US20040095477A1 - ROI setting method and apparatus, electronic camera apparatus, program, and recording medium - Google Patents
ROI setting method and apparatus, electronic camera apparatus, program, and recording medium Download PDFInfo
- Publication number
- US20040095477A1 US20040095477A1 US10/637,420 US63742003A US2004095477A1 US 20040095477 A1 US20040095477 A1 US 20040095477A1 US 63742003 A US63742003 A US 63742003A US 2004095477 A1 US2004095477 A1 US 2004095477A1
- Authority
- US
- United States
- Prior art keywords
- roi
- recognition
- region
- image data
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Abandoned
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/60—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using transform coding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
- H04N19/134—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the element, parameter or criterion affecting or controlling the adaptive coding
- H04N19/136—Incoming video signal characteristics or properties
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
- H04N19/134—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the element, parameter or criterion affecting or controlling the adaptive coding
- H04N19/136—Incoming video signal characteristics or properties
- H04N19/14—Coding unit complexity, e.g. amount of activity or edge presence estimation
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
- H04N19/134—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the element, parameter or criterion affecting or controlling the adaptive coding
- H04N19/162—User input
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
- H04N19/169—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding
- H04N19/17—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/24—Aligning, centring, orientation detection or correction of the image
- G06V10/248—Aligning, centring, orientation detection or correction of the image by interactive preprocessing or interactive shape modelling, e.g. feature points assigned by a user
Definitions
- the present invention relates generally to the field of image processing, and particularly to a technique for setting a region of interest (ROI) of an image in an electronic processing apparatus such as an electronic camera.
- ROI region of interest
- a captured image is usually compressed before it is recorded on a recording medium.
- JPEG is widely used for compressing image data; however, a significant amount of research is being done to promote the use of a new image compression technique, JPEG 2000 (ISO/IEC FCD 15444-1).
- JPEG 2000 has a selective region image quality improvement function (ROI function) for reducing the compression rate (improving the image quality) of a region of interest (ROI) of an image without reducing the compression rate of the overall image.
- ROI function region image quality improvement function
- This ROI function is particularly appealing to an electronic camera.
- high image quality can be maintained in the important region while the amount of data of the overall image other than the important region can be significantly reduced.
- a publicly known technique for specifying the ROI is disclosed in Japanese Patent Laid-Open Publication No.2001-230947, for example.
- an electronic camera having an EVF (electronic view finder) screen that displays a guidance frame or a template image is disclosed.
- the guidance frame or template image is used as a base image for framing and capturing an image.
- a region within the guidance frame or a region other than the template image is handled as the ROI in the compression process of the captured image.
- the ROI information is recorded on a header of a corresponding image file, and thus the ROI can be displayed on the rest of the reproduced image in the image reproduction process.
- Japanese Patent Laid-Open Publication No.2001-119625 discloses a digital camera that determines a range of a main object of a captured image based on a user operation, handles this range as an ROI, compresses the corresponding range at a lower compression rate than that for the rest of the regions, and describes the ROI information on a header of a corresponding compressed image file.
- This Japanese patent application mentions that the range of the main object may be determined automatically based on edge or histogram information of the image.
- JPEG 2000 there appears to be no mention of JPEG 2000 in this Japanese patent application.
- the ROI setting method using a guidance frame or a template image as disclosed in Japanese Patent Laid-Open Publication No.2001-230947 limits the flexibility of the framing and scene capturing operation.
- an ROI setting apparatus comprises ROI recognition modules each for recognizing an ROI of image data according to a predetermined method and to obtain a recognition result, and an ROI control unit adapted to select an ROI recognition module out of the plurality of ROI recognition modules and set ROI information based on the recognition result obtained by the selected ROI recognition module.
- FIG. 1 is a schematic block diagram illustrating an embodiment of the present invention
- FIG. 2 is a schematic block diagram illustrating JPEG 2000 image compression/decompression algorithms
- FIGS. 3 A- 3 D are diagrams illustrating two-dimensional wavelet conversion processes
- FIG. 4 is a diagram showing a configuration of compressed image data (code stream) generated according to the JPEG 2000;
- FIG. 5 is a flowchart of an ROI setting operation
- FIG. 6 is a flowchart of an operation shown in FIG. 5;
- FIG. 7 is a flowchart of the operation of an ROI recognition module ( 1 );
- FIG. 8 is a flowchart of the operation of an alternative ROI recognition module ( 2 );
- FIG. 9 is a flowchart of the operation of another alternative ROI recognition module ( 3 );
- FIG. 10 is a flowchart of the operation of another alternative ROI recognition module ( 4 );
- FIG. 11 is a flowchart of the operation of another alternative ROI recognition module ( 5 );
- FIG. 12 is a flowchart of the operation of another alternative ROI recognition module ( 6 );
- FIG. 13 is a flowchart of the operation of another alternative ROI recognition module ( 7 );
- FIG. 14 is a flowchart of the operation of another alternative ROI recognition module ( 8 );
- FIG. 15 is a flowchart of the operation of another alternative ROI recognition module ( 9 );
- An ROI setting apparatus and method that can include a more practical ROI setting function in an image processing apparatus such as an electronic camera apparatus are described.
- One embodiment of the present invention provides an electronic camera apparatus such as a digital camera with a more practical ROI setting function.
- an ROI setting apparatus includes: multiple ROI recognition modules each adapted for recognizing an ROI of image data according to a predetermined method and thereby obtaining a recognition result; and an ROI control unit adapted to select an ROI recognition module out of the ROI recognition modules and set ROI information based on the recognition result obtained by the selected ROI recognition modules.
- the term “module,” for purposes herein, may comprise hardware (e.g., circuitry, dedicated logic, etc.), software (such as is run on a general purpose computer system or a dedicated machine), or a combination of both.
- the terms “module” and “unit” may be used interchangeably.
- the ROI setting apparatus may be used in a successive capturing of still images or a capturing of moving images.
- the ROI control unit may select the ROI recognition module according to an instruction from a user.
- the user is able to change the ROI recognition method as desired so that a desired ROI setting operation may be performed.
- the ROI control unit may select the ROI recognition module according to a scene type selected by a user.
- the user can select a scene type and the ROI can be set according to a higher quality ROI recognition method for this scene type.
- the ROI control unit may set the ROI information based on a region selected out of a plurality of regions recognized by the selected ROI recognition module, the region being selected, for example, according to an instruction from a user.
- the user is able to make corrections on the automatically recognized ROI to set an ROI suiting the preference of the user.
- the ROI control unit may enlarge or reduce a region recognized by the selected ROI recognition module according to an instruction from a user.
- the user is able to make corrections on the automatically recognized ROI to set an ROI suiting the preference of the user.
- the ROI recognition module may each include a recognition condition
- the ROI control unit may change the recognition condition of the selected ROI recognition module according to an instruction from a user. The user is able to adjust the ROI recognition condition to set an ROI suiting the preference of the user.
- At least one of the ROI recognition modules may detect a region of the image data containing a face and using the region as a base region to recognize the ROI.
- a face portion of a portrait image for example, can be set as the ROI.
- At least one of the ROI recognition modules may detect a region of the image data in which high frequency components are concentrated and using the region as a base region to recognize the ROI.
- An intricate portion of a landscape image for example, can be set as the ROI.
- At least one of the ROI recognition modules may detect a region of the image data in which patterns having a striking contrast are concentrated and using the region as a base region to recognize the ROI.
- a region of the image containing a barcode or letters can be set as the ROI.
- At least one of the ROI recognition modules may detect a region at a center portion of the image data containing an object and using the region as a base region to recognize the ROI.
- a region containing an object, which is oftentimes at the center portion of the image, can be set as the ROI.
- At least one of the ROI recognition modules may use an AF evaluation region used in an image capturing operation of the image data as a base image to recognize the ROI.
- a region containing an object on which the focus is directed can be set as the ROI.
- At least one of the ROI recognition modules may use an AE evaluation region used in an image capturing operation of the image data as a base image to recognize the ROI.
- a region containing an object on which the exposure is directed can be set as the ROI.
- At least one of the ROI recognition modules may detect a region of the image data in which movement is perceived and using the region as a base region to recognize the ROI.
- a region containing the moving object in a captured image of a moving object can be set as the ROI.
- At least one of the ROI recognition modules may extract a region of the image data that is significantly brighter than a corresponding region of monitoring image data obtained right before an image capturing operation and using the region as a base region to recognize the ROI.
- a portion of a captured flash image containing the object, which is positioned close by, can be set as the ROI.
- At least one of the ROI recognition modules may detect a high brightness region of the image data and using the region as a base region to recognize the ROI.
- a bright portion of the image containing the object can be set as the ROI.
- At least one of the ROI recognition modules may detect a high brightness region of the image data, subtracting from the region a high brightness region portion at a predetermined portion of the image data, and using the resulting region as a base region to recognize the ROI.
- a bright portion of the image except for upper portion of the image representing the sky can be set as the ROI.
- At least one of the ROI recognition modules may recognize the ROI based on a packet size of compressed data of the image data.
- tile data are packets of respective regions called precincts, and a precinct with a large packet size (amount of codes) is likely to be an important portion of the image.
- the ROI can be set based on the packet size of each precinct.
- an electronic camera apparatus includes an ROI setting apparatus as described herein.
- an optimum ROI can be set for a variety of captured scenes and the ROI can also be set according to the preference of the user
- a program administers a computer to function as multiple ROI recognition modules and an ROI control unit of the ROI setting apparatus.
- a computer readable recording medium stores a program according to the present invention.
- the ROI setting apparatus of the present invention can be realized by a computer such as a personal computer or a microcomputer.
- an ROI setting method includes: selecting an ROI recognition method out of multiple ROI recognition methods; recognizing an ROI of image data according to the selected ROI recognition method to obtain a recognition result; and setting ROI information based on the obtained recognition result
- FIG. 2 is a schematic block diagram illustrating image compression/decompression processes according to JPEG 2000.
- image data being subjected to the compression process e.g., image data of each frame in a case where moving images are handled
- image data of each frame in a case where moving images are handled are divided into rectangular regions called tiles that do not overlap with one another.
- a level shift operation and a color space conversion process are performed in order to raise the compression rate.
- the level shift operation involves subtracting half a dynamic range from an integral value such as an RGB value that has no codes.
- the level shift operation is not performed on an integral value having a code, and thus, if the input image data corresponds to YCrCb data, for example, the Cr and Cb components, which have attached codes, do not go through the level shift operation.
- the color space conversion process involves converting input image data into YCrCb data when the input image data correspond to RGB data or CMY data. It is noted that in an alternative embodiment, this DC level/color space conversion/de-conversion unit 200 may be omitted.
- a two-dimensional wavelet conversion (discrete wavelet transform: DWT) is performed on the image data of each component of each tile that has been processed by the DC level/color space conversion/de-conversion unit 200 .
- DWT discrete wavelet transform
- FIGS. 3 A- 3 D are diagrams illustrating an exemplary two-dimensional wavelength conversion process in a case where the decomposition level is 3.
- a tile image shown in FIG. 3A is divided into sub bands 1 LL, 1 HL, 1 LH, and 1 HH as shown in FIG. 3B.
- the sub band 1 LL is divided into sub bands 2 LL, 2 HL, 2 LH, and 2 HH as shown in FIG. 3C.
- the sub band 2 LL is divided into sub bands 3 LL, 3 HL, 3 LH, and 3 HH, as shown in FIG. 3D.
- each of the sub band coefficients obtained from a recursive division (octave division) of the low frequency components (coefficients of sub band LL) are quantized by a quantization/de-quantization unit 204 , after which the data is encoded by an entropy coding/decoding unit 206 .
- a quantization/de-quantization unit 204 In JPEG 2000, both reversible compression (lossless compression) and irreversible compression (lossy compression) are possible. In the case of a reversible compression, the quantization step width is 1, and quantization is not actually performed at this stage.
- the entropy coding/decoding unit 206 performs entropy coding on wavelet coefficients.
- a block-base bit plane coding scheme called EBCOT Embedded Block Coding with Optimized Truncation
- the wavelet coefficients being subjected to coding are either positive or negative integers, and while a scanning operation of these coefficients is performed in a designated order, the coding is performed on the coefficients represented in absolute values one bit plane at a time from a higher bit plane to a lower bit plane.
- a code sequence generated at the entropy coding/decoding unit 206 is sent to the tag processing unit 208 where the code sequence is arranged into a code stream with tag information attached thereto, after which the code stream is output.
- FIG. 4 is a diagram illustrating a configuration of the code stream (compressed image data).
- the code stream begins with an SOC marker, which is followed by a main header describing a parameter for the coding operation or a parameter for the quantization process, for example.
- the code stream of each tile follows.
- the code stream of each tile starts with an SOT marker, followed by a tile header, then an SOD marker, and then tile data.
- an EOC marker indicating the end of the code stream is placed after the last tile data set in the code stream.
- Each set of tile data corresponds to a packet of the codes of the coefficients of the sub bands in each region called a precinct.
- One feature of the JPEG 2000 algorithms is the above-described selective region image quality improvement function (ROI function).
- ROI function selective region image quality improvement function
- JPEG 2000 JPEG 2000 Part 1 an ROI method of shifting the wavelet coefficient values of a selected region to a higher bit plane and shifting the wavelet coefficients of the rest of the regions to a lower bit plane before encoding the wavelet coefficients (max-shift method) is used.
- the ROI function may be realized in the quantization process by quantizing the wavelet coefficient values of the ROI using more intricate quantization steps than those for the rest of the regions.
- the ROI method can realize a reduction in the overall amount of codes without degrading the image quality of the ROI of the image.
- the decompression process of the code stream is the reverse process of the compression process. Namely, tag information of an input code stream is read and broken down into a code sequence of the respective components of the respective tiles by use of the tag processing unit 208 . Then, the resulting sequence is decoded into wavelet coefficients in the order according to the tag information by use of the entropy coding/decoding unit 206 .
- the decoded wavelet coefficients are de-quantized by the quantization/de-quantization unit 204 , after which a two-dimensional wavelet de-conversion is performed on the de-quantized data by use of the two-dimensional wavelet conversion/de-conversion unit 202 so that the image data of the respective components of the respective tiles are reproduced. Then the DC level/color space conversion/de-conversion unit 200 performs the reverse conversion of the conversion performed in the compression process on the image data of the respective components of the respective tiles, after which the image is output.
- FIG. 1 is a schematic block diagram illustrating an embodiment of the present invention.
- An electronic camera apparatus shown in this drawing has an image capture unit 100 , a storage unit 102 , a display unit 104 , a compression/decompression unit 106 , a write/read unit 108 , an ROI setting apparatus that includes an ROI control unit 120 and an ROI recognition unit 122 , and an operation unit 124 for a user to input instructions relating to the ROI setting operation.
- the image capture unit 100 captures an image of an object with an image sensor via an optical lens and outputs the captured image data like a conventional image capture unit of a digital camera. Further, the image capture unit 100 has a still image capture mode and a moving image capture mode. Also, the image capture unit 100 may have an auto-focus (AF) function, an auto-exposure (AE) function, and a flash function, for example. In the present embodiment, it is assumed that the electronic camera apparatus uses the AF scheme and the AE scheme to determine the focusing condition or the exposure condition based on a plurality of evaluation regions of an image.
- the storage unit 102 temporarily stores the image data output by the image capture unit 100 or image data decompressed by the compression/decompression unit 106 .
- the display unit 104 displays the image data stored in the storage unit 102 and other information on an LCD panel, for example, and is also used as an EVF (electronic view-finder).
- the compression/decompression unit 106 performs the compression process on the image data and the decompression process on the code stream using the algorithms according to JPEG 2000 as described above.
- the write/read unit 108 writes the code stream output from the compression/decompression unit 106 on a recording medium 110 as an image file, or reading the image file from the recording medium 110 .
- the ROI recognition unit 122 is arranged to automatically recognize the ROI of an image, and includes ten various ROI recognition modules ( 1 ) through ( 10 ) each conforming to an ROI recognition method differing from one another. The ROI recognition method of each of these recognition modules will be described in detail later on.
- the ROI control unit 120 definitively sets the ROI information based on information relating to a selection of the ROI recognition module of the ROI recognition unit 122 , a control of the selected ROI recognition module, and the ROI (candidate) recognized by the ROI recognition module.
- the ROI control unit 120 also stores ROI recognition conditions (parameter values).
- Instructions from a user relating to the ROI setting operation are input from the operation unit 124 to the ROI control unit 120 .
- examples of the instructions input from the operation unit 124 are given.
- the image capture unit 100 supplies image capture condition information such as image capture mode information (information distinguishing between the still image capture mode and the moving image capture mode), flash information (information indicating the flash mode), AF information (information on the AF evaluation region used in the focus evaluation for the image capture operation), AE information (information on the AE evaluation region used in the optimum exposure evaluation for the image capturing operation), and scene selection information (information indicating the type of scene selected by a scene selection switch) to the ROI control unit 120 .
- image capture mode information information distinguishing between the still image capture mode and the moving image capture mode
- flash information information indicating the flash mode
- AF information information on the AF evaluation region used in the focus evaluation for the image capture operation
- AE information information on the AE evaluation region used in the optimum exposure evaluation for the image capturing operation
- scene selection information information indicating the type of scene selected by a scene selection switch
- FIG. 5 is a flowchart illustrating an ROI setting operation involving the user that is performed, for example, each time a still image is captured.
- the instruction (a) to perform the ROI setting operation involving the user may be given during a monitoring operation (or during display of through images) in which images captured by the image capture unit 100 (monitoring images or through images) are successively displayed on the display unit 104 .
- step S 1 the ROI control unit 120 selects one of the ROI recognition modules implemented in the ROI recognition unit 122 .
- an ROI recognition module for the selected scene type according to the scene selection information is selected.
- a default ROI recognition module or an ROI recognition module predesignated by the user is selected.
- the image capture unit 100 performs scene monitoring until a release switch is pushed.
- the image capture unit 100 successively outputs data of the monitoring images, and this data is stored in the storage unit 102 .
- the monitoring images are displayed on the display unit 104 . It is noted that a monitoring image is usually an image in which some of the scanning lines are left out.
- the image capture unit 100 captures a still image.
- the data of the captured still image without the scanning lines being left out are stored in the storage unit 102 , after which this captured image is displayed on the display unit 104 .
- data of at least one monitoring image obtained right before the image capturing operation are also stored in the storage unit 102 .
- step S 2 the ROI control unit 120 administers the selected ROI recognition module to perform an ROI recognition process on this captured still image data, and also administers the display unit 104 to display the recognize ROI on the captured still image.
- the ROI control unit 120 administers the selected ROI recognition module to perform an ROI recognition process on this captured still image data, and also administers the display unit 104 to display the recognize ROI on the captured still image.
- step S 3 if the user inputs an instruction to confirm the ROI via the operation unit 124 , then in step S 5 , the ROI control unit 120 confirms the ROI information based on the current ROI, and sets this information to the compression/decompression unit 106 and the write/read unit 108 . Also, the ROI control unit 120 stores the parameter values used for this ROI recognition process. Then, in step S 6 , the captured still image data stored in the storage unit 102 are compressed by the compression/decompression unit 106 , and the resulting code stream is written on the recording medium 110 as an image file by use of the write/read unit 108 . In this compression process, the ROI is compressed at a compression rate lower than that for the rest of the regions in accordance with the set ROI information. Also, the ROI information is described in the header of the image file.
- the ROI recognition module can be altered.
- the ROI control unit 120 selects an ROI recognition module other than the currently selected ROI recognition module in step S 4 , and administers the newly selected ROI recognition module to perform the ROI recognition process over again and display the recognized ROI on the display unit 104 .
- FIG. 6 is a flowchart illustrating detailed process steps for the operation of step 2 .
- the ROI control unit 120 sets the parameter values (described below) for controlling the recognition conditions for the selected ROI recognition module (method).
- the parameter values may be either default values or values previously used and stored.
- the ROI control unit 120 administers the ROI recognition module to perform ROI recognition and also administers the display unit 104 to display the recognized ROI (still an ROI candidate at this point) on the captured image.
- the user can see the displayed ROI candidate, and can then input instructions (b), (c), and/or (d) as necessary or desired. More specifically, when a plurality of ROI candidates are recognized, the user may, for example, use a cursor on the screen of the display unit 104 to specify the necessary or desired region and the unnecessary region (instruction (b)). Also, the user may use an enlargement/reduction indicator displayed on the screen of the display unit 104 to instruct the enlargement/reduction of the required region from the recognized ROI candidate, or instruct the enlargement/reduction of each individual ROI candidate using a cursor (instruction (c)). Also, the user may use a parameter value indicator displayed on the display unit 104 to instruct an increase or decrease of a parameter value controlling the ROI recognition condition (instruction (d)).
- step S 14 the ROI control unit 120 determines the type of instruction input from the operation unit 124 , and performs the appropriate operation according to the determined instruction.
- step S 15 the ROI control unit 120 invalidates the region(s) selected by the user from among the plurality of recognized ROI candidates.
- the user is able to validate the preferred ROI candidate when a plurality of ROI candidates are recognized.
- This process may be performed repeatedly, and after each time this process is performed, the display is rearranged in step S 12 .
- step S 16 the ROI control unit 120 enlarges or reduces the ROI candidate according to this instruction.
- the user is able to enlarge or reduce the automatically recognized ROI candidate as necessary or desired.
- This process may be performed repeatedly, and after each time this process is performed, the display is rearranged in step S 12 .
- step S 17 the ROI control unit 120 changes the parameter value, and administers the ROI recognition module to perform a recognition process once more so that the newly recognized ROI candidate is displayed on the display unit 104 in step S 12 .
- a face portion recognition process is performed on the image data in step S 21 so that the eyes, nose, mouth and other facial features of a person are particularly taken into consideration and a center region of a person's face is detected from the image.
- a range having significant contrast and including the center region (base region) is detected, and in step S 23 , the detected range is slightly enlarged and this enlarged range is recognized as an ROI candidate.
- a significant contrast determination threshold value and/or an extent of enlargement of the range correspond to the parameter values of this ROI recognition module ( 1 ).
- this ROI recognition module ( 1 ) is selected when a ‘person’ is selected as the scene type by the scene selection switch.
- the range detected in step S 22 may be used as the ROI candidate without being enlarged.
- a region of the image in which high frequency components are concentrated is detected in step S 31 .
- a range having significant contrast and including this region (base region) is detected, and in step S 33 , the detected range is slightly enlarged and this enlarged range is recognized as an ROI candidate.
- a high frequency component detection threshold value, the significant contrast determination threshold value, and/or the extent of enlargement of the range correspond to the parameter values of this ROI recognition module ( 2 ).
- the range detected in step S 32 maybe used as the ROI candidate without being enlarged.
- a region of the image in which patterns with striking contrast such as a bar code or letters are concentrated is detected in step S 41 .
- step S 42 a range having significant contrast and including this region (base region) is detected, and in step S 43 , the detected range is slightly enlarged and the enlarged range is recognized as an ROI candidate.
- a striking contrast determination threshold value, the significant contrast determination threshold value, and/or the extent of enlargement of the range correspond to the parameter values of this ROI recognition module ( 3 ).
- the range detected in step S 42 may be used as the ROI candidate without being enlarged.
- an object in a center portion of the image is recognized in step S 51 .
- a range having significant contrast and including the recognized object region (base region) is detected.
- the detected range is slightly enlarged and this enlarged range is recognized as an ROI candidate.
- the significant contrast determination threshold value and/or the extent of enlargement of the range correspond to the parameter values of this ROI recognition module ( 4 ).
- the range detected in step S 52 can be used as the ROI candidate without being enlarged.
- a range having significant contrast and including a final AF evaluation region used in a focus determination is detected in step S 61 .
- the detected range is slightly enlarged and this enlarged range is recognized as an ROI candidate.
- the significant contrast determination threshold value and/or the extent of enlargement of the range correspond to the parameter values of this ROI recognition module ( 5 ).
- the range detected in step S 61 may be used as the ROI candidate without being enlarged.
- the AF information obtained upon capturing this image may be recorded on the header of the corresponding image file.
- a range having significant contrast and including a final AE evaluation region (provided by the image capture unit 100 as AE information) used in an optimum exposure determination is detected in step S 71 .
- the detected range is slightly enlarged and this enlarged range is recognized as an ROI candidate.
- the significant contrast determination threshold value and/or the extent of enlargement of the range correspond to the parameter values of this ROI recognition module ( 6 ).
- the range detected in step S 71 may be used as the ROI candidate without being enlarged.
- the AE information obtained upon capturing this image may be recorded on the header of the corresponding image file.
- a range having significant contrast and including this region (base region) is detected in step S 82 .
- the detected range is slightly enlarged and this enlarged region is recognized as an ROI candidate.
- a movement determination threshold value, the significant contrast determination threshold value, and/or the extent of enlargement of the range correspond to the parameter values of this ROI recognition module ( 7 ).
- the range detected in step S 82 may be used as the ROI candidate without being enlarged.
- This ROI recognition module is selected when a ‘moving object’ is selected as the scene type by the scene selection switch. Also, in order to use the ROI recognition module ( 7 ) on a still image recorded in a recording medium 110 , the range in which movement occurs may be detected in the image capturing stage and this information may be recorded on the header of the corresponding image file.
- ROI recognition module ( 8 ) which is used in a flash image capture operation
- a region of a subjected image e.g., person or some other object
- a range having significant contrast and including this region base region
- step S 93 the detected range is slightly enlarged and the enlarged range is recognized as an ROI candidate.
- a threshold value for determining a region to be brighter in the subjected image than in the idle image, the significant contrast determination threshold value, and/or the extent of enlargement of the range correspond to the parameter values of this ROI recognition module ( 8 ). Further, the range detected in step S 92 may be used as the ROI candidate without being enlarged.
- a high brightness region of the image is detected in step S 101 , and then in step S 102 , a range having significant contrast and including this region (base region) is detected. Then, in step S 103 , the detected range is slightly enlarged and this enlarged range is recognized as an ROI candidate.
- a high brightness determination threshold value, the significant contrast determination threshold value, and/or the extent of enlargement of the range correspond to the parameter values of this ROI recognition module ( 9 ). Further, the range detected in step S 102 may be used as the ROI candidate without being enlarged.
- ROI recognition module ( 10 ) recognizes a region in a manner identical to that of the ROI recognition module ( 9 ). However, the ROI recognition module ( 10 ) further subtracts a high brightness region portion having an area exceeding a predetermined value and being situated in a predetermined region (e.g., an upper region) of the image (e.g., a region corresponding to the sky) from the high brightness region detected by the ROI recognition module ( 9 ), and recognizes the resulting region as the ROI candidate.
- a predetermined region e.g., an upper region
- step S 1 the ROI control unit 120 selects the ROI recognition module predesignated by the user or the ROI recognition module corresponding to the scene type selected by the scene selection switch.
- step S 2 an ROI candidate is recognized by the ROI recognition module for each captured image.
- the parameter values for the ROI recognition process if parameter values for the selected ROI recognition module are stored, the stored parameter values are used, and if there are no parameter values stored for the selected recognition module, default parameter values are set to the ROI recognition module.
- step S 5 without waiting for the confirmation instruction from the user, the recognized ROI candidate is confirmed as the ROI, and this ROI information is set to the compression/decompression unit 106 and the write/read unit 108 .
- a change in the ROI recognition module may be made (step S 4 ), a selection of the region (FIG. 6, step S 15 ), an enlargement/reduction of the region (FIG. 6, step S 16 ), and a change in the parameter values (FIG. 6, step S 17 ) may not be performed.
- the user may intervene in setting the ROI of the still image or each of the frame images of the moving image that is compressed through lossless compression or low rate compression and recorded on the recording medium 110 .
- the operation performed in this case is descried below with reference to FIG. 5.
- thumbnail images or lists of a plurality of images already recorded on the recording medium 110 may be displayed on the display unit 104 , and the user is able to select a desired image.
- the corresponding image file is read out by the write/read unit 108 and decompressed by the compression/decompression unit 106 . Then the decompressed image data is stored in the storage unit 102 , and the image is displayed on the display unit 104 . Then, in step S 2 , the ROI is recognized by use of the selected ROI recognition module. The rest of the operation is identical to the ROI setting operation of a direct continuation of the image capture operation. However, the ROI recognition module ( 5 ) and/or ROI recognition module ( 6 ) may not be used unless AF information and/or AE information is described in the header of the corresponding image file.
- the ROI recognition module ( 7 ) and ROI recognition module ( 8 ) may not be used.
- the ROI recognition module ( 7 ) may be used since movement can be detected between consecutive frame images, but the ROI recognition module ( 8 ) may not be used.
- the ROI control unit 120 administers the display unit 104 to display the ROI on the image according to this ROI information.
- the ROI recognition unit 122 is used.
- an ROI recognition method without using the ROI recognition unit 122 can also be realized. An example of such operation is described below with reference to FIG. 5.
- the ROI control unit 120 administers the compression/decompression unit 106 to perform a lossless or a low rate compression process on the image data in step S 2 .
- the compression process may be performed on the wavelet coefficients at decomposition level 1 , for example.
- the size (amount of codes) of each packet in each tile data is obtained by the compression/decompression unit 106 , and this is compared with the determination threshold value.
- a region (precinct) corresponding to a packet having a size greater than the determination threshold value is recognized as the ROI.
- the ROI control unit 120 co-operates with the compression/decompression unit 106 to function as the ROI recognition module.
- the method for performing the ROI recognition may be set independently from the ROI control unit 120 .
- the ROI information is set to the compression/decompression unit 106 so that the compression process is performed.
- the ROI information is set to the write/read unit 108 so that the information is described in the header of the image file that is to be written on the recording medium 110 .
- ROI recognition involving a user is also possible in this ROI recognition method.
- the user is able to instruct selection of a region (corresponding to FIG. 6 step S 15 ), enlargement/reduction of a region (corresponding to FIG. 6 step S 16 ), and/or change of a packet size determination threshold value (corresponding to FIG. 6 step S 17 ), for example.
- the ROI control unit 120 confirms the ROI and sets the ROI information (FIG. 5 step S 5 ).
- the compression/decompression unit 106 may alternatively be arranged to perform the compression process without taking the ROI into consideration, and the header of a packet having a size exceeding the packet size determination threshold value may be rewritten so that a precinct corresponding to this packet is arranged to be the ROI.
- the ROI control unit 120 may also be realized by programs implemented in a computer such as a personal computer or a microcomputer. Such programs and various recording (storage) mediums on which the programs are recorded are also included in the scope of the present invention.
- the ROI setting apparatus and method according to the present invention is not limited to implementation in an electronic camera apparatus such as a digital camera and its method; rather, the present invention may be applied to various other types of image processing apparatuses that can record an image through image compression.
- an image processing apparatus such as an electronic camera apparatus is able to reduce limitations in the framing of an image while also reducing the trouble arising from a completely manual operation. Further, the present invention may be adapted for various scenes and user preferences, and is able to realize a practical ROI setting function that is applicable to various operations such as a successive capturing of still images or a capturing of a moving image.
Abstract
An ROI setting apparatus including an ROI recognition unit and an ROI control unit is provided. In one embodiment, the ROI recognition unit contains multiple ROI recognition modules for recognizing an ROI of image data according to various methods to obtain a recognition result. The ROI control unit selects one ROI recognition module out of the ROI recognition modules and sets ROI information based on the recognition result. The ROI recognition module may be selected according to an instruction from a user input via an operation unit, or a scene type selected by a scene selection switch of an image capture unit. The ROI control unit may perform operations such as selecting, enlarging, or reducing the ROI recognized by the ROI recognition module, or changing the ROI recognition conditions according to the respective instructions from the user input via the operation unit.
Description
- The present application claims priority to the corresponding Japanese Application No. 2002-232475 filed on Aug. 9, 2002, the entire contents of which are hereby incorporated by reference.
- 1. Field of the Invention
- The present invention relates generally to the field of image processing, and particularly to a technique for setting a region of interest (ROI) of an image in an electronic processing apparatus such as an electronic camera.
- 2. Description of the Related Art
- In an electronic apparatus such as a digital camera, a captured image is usually compressed before it is recorded on a recording medium.
- Presently, JPEG is widely used for compressing image data; however, a significant amount of research is being done to promote the use of a new image compression technique, JPEG 2000 (ISO/IEC FCD 15444-1). JPEG 2000 has a selective region image quality improvement function (ROI function) for reducing the compression rate (improving the image quality) of a region of interest (ROI) of an image without reducing the compression rate of the overall image.
- This ROI function is particularly appealing to an electronic camera. By setting an important region of a captured image as the ROI, high image quality can be maintained in the important region while the amount of data of the overall image other than the important region can be significantly reduced.
- To use the ROI function, it is necessary to specify an ROI in each individual captured image. A publicly known technique for specifying the ROI is disclosed in Japanese Patent Laid-Open Publication No.2001-230947, for example. In this Japanese application, an electronic camera having an EVF (electronic view finder) screen that displays a guidance frame or a template image is disclosed. The guidance frame or template image is used as a base image for framing and capturing an image. Then, a region within the guidance frame or a region other than the template image is handled as the ROI in the compression process of the captured image. Also, the ROI information is recorded on a header of a corresponding image file, and thus the ROI can be displayed on the rest of the reproduced image in the image reproduction process.
- Also, Japanese Patent Laid-Open Publication No.2001-119625 discloses a digital camera that determines a range of a main object of a captured image based on a user operation, handles this range as an ROI, compresses the corresponding range at a lower compression rate than that for the rest of the regions, and describes the ROI information on a header of a corresponding compressed image file. This Japanese patent application mentions that the range of the main object may be determined automatically based on edge or histogram information of the image. However, there appears to be no mention of JPEG 2000 in this Japanese patent application.
- The ROI setting method using a guidance frame or a template image as disclosed in Japanese Patent Laid-Open Publication No.2001-230947 limits the flexibility of the framing and scene capturing operation.
- Also, with the method of manually setting the range of the main object as the ROI as disclosed in Japanese Patent Laid-Open Publication No.2001-119625, there is a problem in that the manual operation can be quite troublesome and the method may not be used for successive capturing of still images or capturing of moving images. Although mention is made of automatically determining the range of the main object based on the edge or histogram of the image, a specific method for determining the ROI does not appear to be disclosed in this Japanese patent application. The legitimacy of the determined ROI depends upon such factor as this determination method.
- Also, generally speaking, a wide variety of scene capturing operations need to be considered in automating the ROI setting operation. Further, since user preferences may vary considerably, it may be more practical to enable a user to intervene in the capturing operation to a certain degree.
- An ROI setting technique is disclosed. In one embodiment, an ROI setting apparatus comprises ROI recognition modules each for recognizing an ROI of image data according to a predetermined method and to obtain a recognition result, and an ROI control unit adapted to select an ROI recognition module out of the plurality of ROI recognition modules and set ROI information based on the recognition result obtained by the selected ROI recognition module.
- FIG. 1 is a schematic block diagram illustrating an embodiment of the present invention;
- FIG. 2 is a schematic block diagram illustrating JPEG 2000 image compression/decompression algorithms;
- FIGS.3A-3D are diagrams illustrating two-dimensional wavelet conversion processes;
- FIG. 4 is a diagram showing a configuration of compressed image data (code stream) generated according to the JPEG 2000;
- FIG. 5 is a flowchart of an ROI setting operation;
- FIG. 6 is a flowchart of an operation shown in FIG. 5;
- FIG. 7 is a flowchart of the operation of an ROI recognition module (1);
- FIG. 8 is a flowchart of the operation of an alternative ROI recognition module (2);
- FIG. 9 is a flowchart of the operation of another alternative ROI recognition module (3);
- FIG. 10 is a flowchart of the operation of another alternative ROI recognition module (4);
- FIG. 11 is a flowchart of the operation of another alternative ROI recognition module (5);
- FIG. 12 is a flowchart of the operation of another alternative ROI recognition module (6);
- FIG. 13 is a flowchart of the operation of another alternative ROI recognition module (7);
- FIG. 14 is a flowchart of the operation of another alternative ROI recognition module (8);
- FIG. 15 is a flowchart of the operation of another alternative ROI recognition module (9);
- An ROI setting apparatus and method that can include a more practical ROI setting function in an image processing apparatus such as an electronic camera apparatus are described. One embodiment of the present invention provides an electronic camera apparatus such as a digital camera with a more practical ROI setting function.
- In one embodiment of the present invention, an ROI setting apparatus includes: multiple ROI recognition modules each adapted for recognizing an ROI of image data according to a predetermined method and thereby obtaining a recognition result; and an ROI control unit adapted to select an ROI recognition module out of the ROI recognition modules and set ROI information based on the recognition result obtained by the selected ROI recognition modules. The term “module,” for purposes herein, may comprise hardware (e.g., circuitry, dedicated logic, etc.), software (such as is run on a general purpose computer system or a dedicated machine), or a combination of both. The terms “module” and “unit” may be used interchangeably.
- Since multiple different ROI recognition modules corresponding to ROI recognition methods can be used, a suitable ROI setting operation can be performed for various image data of various captured scenes. Notably, the ROI setting apparatus may be used in a successive capturing of still images or a capturing of moving images.
- Further, in one embodiment, the ROI control unit may select the ROI recognition module according to an instruction from a user. The user is able to change the ROI recognition method as desired so that a desired ROI setting operation may be performed.
- In an embodiment of the present invention, the ROI control unit may select the ROI recognition module according to a scene type selected by a user. The user can select a scene type and the ROI can be set according to a higher quality ROI recognition method for this scene type.
- Further, in an embodiment of the present invention, the ROI control unit may set the ROI information based on a region selected out of a plurality of regions recognized by the selected ROI recognition module, the region being selected, for example, according to an instruction from a user. The user is able to make corrections on the automatically recognized ROI to set an ROI suiting the preference of the user.
- Additionally, in an embodiment of the present invention, the ROI control unit may enlarge or reduce a region recognized by the selected ROI recognition module according to an instruction from a user. The user is able to make corrections on the automatically recognized ROI to set an ROI suiting the preference of the user.
- Also, in an embodiment of the present invention, the ROI recognition module may each include a recognition condition, and the ROI control unit may change the recognition condition of the selected ROI recognition module according to an instruction from a user. The user is able to adjust the ROI recognition condition to set an ROI suiting the preference of the user.
- Further, in an embodiment of the present invention, at least one of the ROI recognition modules may detect a region of the image data containing a face and using the region as a base region to recognize the ROI. A face portion of a portrait image, for example, can be set as the ROI.
- Additionally, in an embodiment of the present invention, at least one of the ROI recognition modules may detect a region of the image data in which high frequency components are concentrated and using the region as a base region to recognize the ROI. An intricate portion of a landscape image, for example, can be set as the ROI.
- Also, in an embodiment of the present invention, at least one of the ROI recognition modules may detect a region of the image data in which patterns having a striking contrast are concentrated and using the region as a base region to recognize the ROI. A region of the image containing a barcode or letters can be set as the ROI.
- Additionally, in an embodiment of the present invention, at least one of the ROI recognition modules may detect a region at a center portion of the image data containing an object and using the region as a base region to recognize the ROI. A region containing an object, which is oftentimes at the center portion of the image, can be set as the ROI.
- Also, in an embodiment of the present invention, at least one of the ROI recognition modules may use an AF evaluation region used in an image capturing operation of the image data as a base image to recognize the ROI. A region containing an object on which the focus is directed can be set as the ROI.
- Additionally, in an embodiment of the present invention, at least one of the ROI recognition modules may use an AE evaluation region used in an image capturing operation of the image data as a base image to recognize the ROI. A region containing an object on which the exposure is directed can be set as the ROI.
- Also, in an embodiment of the present invention, at least one of the ROI recognition modules may detect a region of the image data in which movement is perceived and using the region as a base region to recognize the ROI. A region containing the moving object in a captured image of a moving object can be set as the ROI.
- Additionally, in an embodiment of the present invention, at least one of the ROI recognition modules may extract a region of the image data that is significantly brighter than a corresponding region of monitoring image data obtained right before an image capturing operation and using the region as a base region to recognize the ROI. A portion of a captured flash image containing the object, which is positioned close by, can be set as the ROI.
- Also, in an embodiment of the present invention, at least one of the ROI recognition modules may detect a high brightness region of the image data and using the region as a base region to recognize the ROI. A bright portion of the image containing the object can be set as the ROI.
- Additionally, in an embodiment of the present invention, at least one of the ROI recognition modules may detect a high brightness region of the image data, subtracting from the region a high brightness region portion at a predetermined portion of the image data, and using the resulting region as a base region to recognize the ROI. A bright portion of the image except for upper portion of the image representing the sky can be set as the ROI.
- Also, in an embodiment of the present invention, at least one of the ROI recognition modules may recognize the ROI based on a packet size of compressed data of the image data. As is described below, according to JPEG 2000, tile data are packets of respective regions called precincts, and a precinct with a large packet size (amount of codes) is likely to be an important portion of the image. The ROI can be set based on the packet size of each precinct.
- In another embodiment, an electronic camera apparatus includes an ROI setting apparatus as described herein. In one embodiment, an optimum ROI can be set for a variety of captured scenes and the ROI can also be set according to the preference of the user
- In one embodiment, a program administers a computer to function as multiple ROI recognition modules and an ROI control unit of the ROI setting apparatus. Further, in another embodiment, a computer readable recording medium stores a program according to the present invention. By using such program and/or recording medium, the ROI setting apparatus of the present invention can be realized by a computer such as a personal computer or a microcomputer.
- In another embodiment of the present invention, an ROI setting method includes: selecting an ROI recognition method out of multiple ROI recognition methods; recognizing an ROI of image data according to the selected ROI recognition method to obtain a recognition result; and setting ROI information based on the obtained recognition result
- In embodiments of the present invention described below, algorithms conforming to JPEG 2000 are used in the compression process of an image. Image compression algorithms according to JPEG 2000 are descried in detail inNext Generation Image Encoding Technique JPEG 2000, Yasuyuki Nomizu, Triceps, Co. Ltd., for example. In the following, a brief description of the algorithms is given with reference to FIGS. 2 through 4.
- FIG. 2 is a schematic block diagram illustrating image compression/decompression processes according to JPEG 2000. Herein, image data being subjected to the compression process (e.g., image data of each frame in a case where moving images are handled) are divided into rectangular regions called tiles that do not overlap with one another. In a DC level/color space conversion/
de-conversion unit 200, a level shift operation and a color space conversion process are performed in order to raise the compression rate. The level shift operation involves subtracting half a dynamic range from an integral value such as an RGB value that has no codes. The level shift operation is not performed on an integral value having a code, and thus, if the input image data corresponds to YCrCb data, for example, the Cr and Cb components, which have attached codes, do not go through the level shift operation. The color space conversion process involves converting input image data into YCrCb data when the input image data correspond to RGB data or CMY data. It is noted that in an alternative embodiment, this DC level/color space conversion/de-conversion unit 200 may be omitted. - Then, in a two-dimensional wavelet conversion/
de-conversion unit 202, a two-dimensional wavelet conversion (discrete wavelet transform: DWT) is performed on the image data of each component of each tile that has been processed by the DC level/color space conversion/de-conversion unit 200. - FIGS.3A-3D are diagrams illustrating an exemplary two-dimensional wavelength conversion process in a case where the decomposition level is 3. Specifically, with the two-dimensional wavelet conversion process, a tile image shown in FIG. 3A is divided into sub bands 1LL, 1HL, 1LH, and 1HH as shown in FIG. 3B. Then, by performing a further two-dimensional wavelet conversion on the coefficients of the sub band 1LL, the sub band 1LL is divided into sub bands 2LL, 2HL, 2LH, and 2HH as shown in FIG. 3C. Then, by performing a further two-dimensional wavelet conversion on the coefficients of the sub band 2LL, the sub band 2LL is divided into sub bands 3LL, 3HL, 3LH, and 3HH, as shown in FIG. 3D.
- Referring back to FIG. 2, each of the sub band coefficients obtained from a recursive division (octave division) of the low frequency components (coefficients of sub band LL) are quantized by a quantization/
de-quantization unit 204, after which the data is encoded by an entropy coding/decoding unit 206. In JPEG 2000, both reversible compression (lossless compression) and irreversible compression (lossy compression) are possible. In the case of a reversible compression, the quantization step width is 1, and quantization is not actually performed at this stage. - The entropy coding/
decoding unit 206 performs entropy coding on wavelet coefficients. In the above entropy coding, a block-base bit plane coding scheme called EBCOT (Embedded Block Coding with Optimized Truncation) including block division, coefficient modeling, and binary arithmetic coding is used. The wavelet coefficients being subjected to coding are either positive or negative integers, and while a scanning operation of these coefficients is performed in a designated order, the coding is performed on the coefficients represented in absolute values one bit plane at a time from a higher bit plane to a lower bit plane. - A code sequence generated at the entropy coding/
decoding unit 206 is sent to thetag processing unit 208 where the code sequence is arranged into a code stream with tag information attached thereto, after which the code stream is output. - FIG. 4 is a diagram illustrating a configuration of the code stream (compressed image data). As is shown in the drawing, the code stream begins with an SOC marker, which is followed by a main header describing a parameter for the coding operation or a parameter for the quantization process, for example. Then, the code stream of each tile follows. The code stream of each tile starts with an SOT marker, followed by a tile header, then an SOD marker, and then tile data. Further, an EOC marker indicating the end of the code stream is placed after the last tile data set in the code stream. Each set of tile data corresponds to a packet of the codes of the coefficients of the sub bands in each region called a precinct.
- Herein, it is noted that the algorithms according to JPEG 2000 have many features other than that of realizing excellent image quality at a high compression rate (low bit rate).
- One feature of the JPEG 2000 algorithms is the above-described selective region image quality improvement function (ROI function). According to the basic method of JPEG 2000 JPEG 2000 Part 1), an ROI method of shifting the wavelet coefficient values of a selected region to a higher bit plane and shifting the wavelet coefficients of the rest of the regions to a lower bit plane before encoding the wavelet coefficients (max-shift method) is used. Alternatively, the ROI function may be realized in the quantization process by quantizing the wavelet coefficient values of the ROI using more intricate quantization steps than those for the rest of the regions. In either case, the ROI method can realize a reduction in the overall amount of codes without degrading the image quality of the ROI of the image.
- Referring back to FIG. 2, the decompression process of the code stream is the reverse process of the compression process. Namely, tag information of an input code stream is read and broken down into a code sequence of the respective components of the respective tiles by use of the
tag processing unit 208. Then, the resulting sequence is decoded into wavelet coefficients in the order according to the tag information by use of the entropy coding/decoding unit 206. The decoded wavelet coefficients are de-quantized by the quantization/de-quantization unit 204, after which a two-dimensional wavelet de-conversion is performed on the de-quantized data by use of the two-dimensional wavelet conversion/de-conversion unit 202 so that the image data of the respective components of the respective tiles are reproduced. Then the DC level/color space conversion/de-conversion unit 200 performs the reverse conversion of the conversion performed in the compression process on the image data of the respective components of the respective tiles, after which the image is output. - FIG. 1 is a schematic block diagram illustrating an embodiment of the present invention. An electronic camera apparatus shown in this drawing has an
image capture unit 100, astorage unit 102, adisplay unit 104, a compression/decompression unit 106, a write/read unit 108, an ROI setting apparatus that includes anROI control unit 120 and anROI recognition unit 122, and anoperation unit 124 for a user to input instructions relating to the ROI setting operation. - The
image capture unit 100 captures an image of an object with an image sensor via an optical lens and outputs the captured image data like a conventional image capture unit of a digital camera. Further, theimage capture unit 100 has a still image capture mode and a moving image capture mode. Also, theimage capture unit 100 may have an auto-focus (AF) function, an auto-exposure (AE) function, and a flash function, for example. In the present embodiment, it is assumed that the electronic camera apparatus uses the AF scheme and the AE scheme to determine the focusing condition or the exposure condition based on a plurality of evaluation regions of an image. - The
storage unit 102 temporarily stores the image data output by theimage capture unit 100 or image data decompressed by the compression/decompression unit 106. Thedisplay unit 104 displays the image data stored in thestorage unit 102 and other information on an LCD panel, for example, and is also used as an EVF (electronic view-finder). The compression/decompression unit 106 performs the compression process on the image data and the decompression process on the code stream using the algorithms according to JPEG 2000 as described above. The write/read unit 108 writes the code stream output from the compression/decompression unit 106 on arecording medium 110 as an image file, or reading the image file from therecording medium 110. - The
ROI recognition unit 122 is arranged to automatically recognize the ROI of an image, and includes ten various ROI recognition modules (1) through (10) each conforming to an ROI recognition method differing from one another. The ROI recognition method of each of these recognition modules will be described in detail later on. TheROI control unit 120 definitively sets the ROI information based on information relating to a selection of the ROI recognition module of theROI recognition unit 122, a control of the selected ROI recognition module, and the ROI (candidate) recognized by the ROI recognition module. TheROI control unit 120 also stores ROI recognition conditions (parameter values). - Instructions from a user relating to the ROI setting operation are input from the
operation unit 124 to theROI control unit 120. In the following, examples of the instructions input from theoperation unit 124 are given. - (a) instruction to perform an ROI setting operation involving the user
- (b) instruction, given during an ROI setting operation involving the user, that instructs the selection of a particular region in a case where a plurality of ROIs (candidates) have been automatically recognized
- (c) instruction, given during an ROI setting operation involving the user, that instructs the enlargement/reduction of the ROI (candidate) that has been automatically recognized
- (d) instruction, given during an ROI setting operation involving the user, that instructs the change of a parameter relating to the ROI recognition process
- (e) instruction to select an ROI recognition method (module)
- (f) instruction to automatically set the ROI of a still image
- (g) instruction to automatically set the ROI upon capturing a moving image
- Also, the
image capture unit 100 supplies image capture condition information such as image capture mode information (information distinguishing between the still image capture mode and the moving image capture mode), flash information (information indicating the flash mode), AF information (information on the AF evaluation region used in the focus evaluation for the image capture operation), AE information (information on the AE evaluation region used in the optimum exposure evaluation for the image capturing operation), and scene selection information (information indicating the type of scene selected by a scene selection switch) to theROI control unit 120. - FIG. 5 is a flowchart illustrating an ROI setting operation involving the user that is performed, for example, each time a still image is captured. In this case, in the still image capture mode, the instruction (a) to perform the ROI setting operation involving the user may be given during a monitoring operation (or during display of through images) in which images captured by the image capture unit100 (monitoring images or through images) are successively displayed on the
display unit 104. - As is shown in FIG. 5, in step S1, the
ROI control unit 120 selects one of the ROI recognition modules implemented in theROI recognition unit 122. In a case where a particular scene type is selected by the scene selection switch of theimage capture unit 100, an ROI recognition module for the selected scene type according to the scene selection information is selected. In a case where the scene type is not selected, a default ROI recognition module or an ROI recognition module predesignated by the user is selected. - The
image capture unit 100 performs scene monitoring until a release switch is pushed. Herein, theimage capture unit 100 successively outputs data of the monitoring images, and this data is stored in thestorage unit 102. Then, the monitoring images are displayed on thedisplay unit 104. It is noted that a monitoring image is usually an image in which some of the scanning lines are left out. - When the release switch is pushed, the
image capture unit 100 captures a still image. The data of the captured still image without the scanning lines being left out are stored in thestorage unit 102, after which this captured image is displayed on thedisplay unit 104. Herein, data of at least one monitoring image obtained right before the image capturing operation are also stored in thestorage unit 102. - In step S2, the
ROI control unit 120 administers the selected ROI recognition module to perform an ROI recognition process on this captured still image data, and also administers thedisplay unit 104 to display the recognize ROI on the captured still image. At this point, it is possible to enlarge/reduce or select the automatically recognized ROI, or to make changes in the parameter values determining the ROI recognition condition, for example. The detailed descriptions of such operations will be described later on. - In step S3, if the user inputs an instruction to confirm the ROI via the
operation unit 124, then in step S5, theROI control unit 120 confirms the ROI information based on the current ROI, and sets this information to the compression/decompression unit 106 and the write/read unit 108. Also, theROI control unit 120 stores the parameter values used for this ROI recognition process. Then, in step S6, the captured still image data stored in thestorage unit 102 are compressed by the compression/decompression unit 106, and the resulting code stream is written on therecording medium 110 as an image file by use of the write/read unit 108. In this compression process, the ROI is compressed at a compression rate lower than that for the rest of the regions in accordance with the set ROI information. Also, the ROI information is described in the header of the image file. - Further, if the user inputs the instruction (e) to select the ROI recognition module after step S2, the ROI recognition module can be altered. In response to his instruction, the
ROI control unit 120 selects an ROI recognition module other than the currently selected ROI recognition module in step S4, and administers the newly selected ROI recognition module to perform the ROI recognition process over again and display the recognized ROI on thedisplay unit 104. - FIG. 6 is a flowchart illustrating detailed process steps for the operation of
step 2. - First, in step S11, the
ROI control unit 120 sets the parameter values (described below) for controlling the recognition conditions for the selected ROI recognition module (method). The parameter values may be either default values or values previously used and stored. Then, in step S12, theROI control unit 120 administers the ROI recognition module to perform ROI recognition and also administers thedisplay unit 104 to display the recognized ROI (still an ROI candidate at this point) on the captured image. - Thus, the user can see the displayed ROI candidate, and can then input instructions (b), (c), and/or (d) as necessary or desired. More specifically, when a plurality of ROI candidates are recognized, the user may, for example, use a cursor on the screen of the
display unit 104 to specify the necessary or desired region and the unnecessary region (instruction (b)). Also, the user may use an enlargement/reduction indicator displayed on the screen of thedisplay unit 104 to instruct the enlargement/reduction of the required region from the recognized ROI candidate, or instruct the enlargement/reduction of each individual ROI candidate using a cursor (instruction (c)). Also, the user may use a parameter value indicator displayed on thedisplay unit 104 to instruct an increase or decrease of a parameter value controlling the ROI recognition condition (instruction (d)). - In step S14, the
ROI control unit 120 determines the type of instruction input from theoperation unit 124, and performs the appropriate operation according to the determined instruction. - In a case where the region selection instruction (b) is input, the process moves on to step S15 where the
ROI control unit 120 invalidates the region(s) selected by the user from among the plurality of recognized ROI candidates. Thus, the user is able to validate the preferred ROI candidate when a plurality of ROI candidates are recognized. This process may be performed repeatedly, and after each time this process is performed, the display is rearranged in step S12. - In a case where the region enlargement/reduction instruction (c) is input, the process moves on to step S16 where the
ROI control unit 120 enlarges or reduces the ROI candidate according to this instruction. Thus, the user is able to enlarge or reduce the automatically recognized ROI candidate as necessary or desired. This process may be performed repeatedly, and after each time this process is performed, the display is rearranged in step S12. - In a case where the parameter alteration instruction (d) is input, the process moves on to step S17 where the
ROI control unit 120 changes the parameter value, and administers the ROI recognition module to perform a recognition process once more so that the newly recognized ROI candidate is displayed on thedisplay unit 104 in step S12. - In the following, each of the ROI recognition modules implemented in the
ROI recognition unit 122 and the respective parameters relating to each of the ROI recognition module will be described. - Referring to FIG. 7, according to ROI recognition module (1), a face portion recognition process is performed on the image data in step S21 so that the eyes, nose, mouth and other facial features of a person are particularly taken into consideration and a center region of a person's face is detected from the image. Then in step S22, a range having significant contrast and including the center region (base region) is detected, and in step S23, the detected range is slightly enlarged and this enlarged range is recognized as an ROI candidate. Herein, a significant contrast determination threshold value and/or an extent of enlargement of the range correspond to the parameter values of this ROI recognition module (1). Further, this ROI recognition module (1) is selected when a ‘person’ is selected as the scene type by the scene selection switch. Also, the range detected in step S22 may be used as the ROI candidate without being enlarged.
- Referring to FIG. 8, according to ROI recognition module (2), a region of the image in which high frequency components are concentrated is detected in step S31. Then in step S32, a range having significant contrast and including this region (base region) is detected, and in step S33, the detected range is slightly enlarged and this enlarged range is recognized as an ROI candidate. Herein, a high frequency component detection threshold value, the significant contrast determination threshold value, and/or the extent of enlargement of the range correspond to the parameter values of this ROI recognition module (2). Further, the range detected in step S32 maybe used as the ROI candidate without being enlarged.
- Referring to FIG. 9, according to ROI recognition module (3), a region of the image in which patterns with striking contrast such as a bar code or letters are concentrated is detected in step S41. Then in step S42, a range having significant contrast and including this region (base region) is detected, and in step S43, the detected range is slightly enlarged and the enlarged range is recognized as an ROI candidate. Herein, a striking contrast determination threshold value, the significant contrast determination threshold value, and/or the extent of enlargement of the range correspond to the parameter values of this ROI recognition module (3). Further, the range detected in step S42 may be used as the ROI candidate without being enlarged.
- Referring to FIG. 10, according to ROI recognition module (4), an object in a center portion of the image is recognized in step S51. Then, in step S52, a range having significant contrast and including the recognized object region (base region) is detected. Then, in step S53, the detected range is slightly enlarged and this enlarged range is recognized as an ROI candidate. Herein, the significant contrast determination threshold value and/or the extent of enlargement of the range correspond to the parameter values of this ROI recognition module (4). Further, the range detected in step S52 can be used as the ROI candidate without being enlarged.
- Referring to FIG. 11, according to ROI recognition module (5), a range having significant contrast and including a final AF evaluation region used in a focus determination (provided by the
image capture unit 100 as AF information) is detected in step S61. Then in step S62, the detected range is slightly enlarged and this enlarged range is recognized as an ROI candidate. Herein, the significant contrast determination threshold value and/or the extent of enlargement of the range correspond to the parameter values of this ROI recognition module (5). Further, the range detected in step S61 may be used as the ROI candidate without being enlarged. Also, in order to use the ROI recognition module (5) on an image recorded in therecording medium 110, the AF information obtained upon capturing this image may be recorded on the header of the corresponding image file. - Referring to FIG. 12, according to ROI recognition module (6), a range having significant contrast and including a final AE evaluation region (provided by the
image capture unit 100 as AE information) used in an optimum exposure determination is detected in step S71. Then, in step S72, the detected range is slightly enlarged and this enlarged range is recognized as an ROI candidate. Herein, the significant contrast determination threshold value and/or the extent of enlargement of the range correspond to the parameter values of this ROI recognition module (6). Further, the range detected in step S71 may be used as the ROI candidate without being enlarged. Also, in order to use the ROI recognition module (6) on an image recorded in arecording medium 110, the AE information obtained upon capturing this image may be recorded on the header of the corresponding image file. - Referring to FIG. 13, according to ROI recognition module (7), a region in which movement can be detected in a subjected image based on a comparison between the subjected image and an idle image immediately preceding the image capture operation, for example, is detected in step S81. Then in step S82, a range having significant contrast and including this region (base region) is detected. Then in step S83, the detected range is slightly enlarged and this enlarged region is recognized as an ROI candidate. Herein, a movement determination threshold value, the significant contrast determination threshold value, and/or the extent of enlargement of the range correspond to the parameter values of this ROI recognition module (7). Further, the range detected in step S82 may be used as the ROI candidate without being enlarged. This ROI recognition module is selected when a ‘moving object’ is selected as the scene type by the scene selection switch. Also, in order to use the ROI recognition module (7) on a still image recorded in a
recording medium 110, the range in which movement occurs may be detected in the image capturing stage and this information may be recorded on the header of the corresponding image file. - Referring to FIG. 14, according to ROI recognition module (8), which is used in a flash image capture operation, a region of a subjected image (e.g., person or some other object) that is significantly brighter than the corresponding region in an idle image right before the flash is turned on is detected in step 91. Then in step S92, a range having significant contrast and including this region (base region) is detected, and in step S93, the detected range is slightly enlarged and the enlarged range is recognized as an ROI candidate. Herein, a threshold value for determining a region to be brighter in the subjected image than in the idle image, the significant contrast determination threshold value, and/or the extent of enlargement of the range correspond to the parameter values of this ROI recognition module (8). Further, the range detected in step S92 may be used as the ROI candidate without being enlarged.
- Referring to FIG. 15, according to ROI recognition module (9), a high brightness region of the image is detected in step S101, and then in step S102, a range having significant contrast and including this region (base region) is detected. Then, in step S103, the detected range is slightly enlarged and this enlarged range is recognized as an ROI candidate. Herein, a high brightness determination threshold value, the significant contrast determination threshold value, and/or the extent of enlargement of the range correspond to the parameter values of this ROI recognition module (9). Further, the range detected in step S102 may be used as the ROI candidate without being enlarged.
- ROI recognition module (10) recognizes a region in a manner identical to that of the ROI recognition module (9). However, the ROI recognition module (10) further subtracts a high brightness region portion having an area exceeding a predetermined value and being situated in a predetermined region (e.g., an upper region) of the image (e.g., a region corresponding to the sky) from the high brightness region detected by the ROI recognition module (9), and recognizes the resulting region as the ROI candidate.
- Now, referring back to FIG. 5, an operation performed upon giving the instruction (f) for automatically setting the ROI in the still image capture mode will be described.
- In this case, in step S1, the
ROI control unit 120 selects the ROI recognition module predesignated by the user or the ROI recognition module corresponding to the scene type selected by the scene selection switch. In step S2, an ROI candidate is recognized by the ROI recognition module for each captured image. As for the parameter values for the ROI recognition process, if parameter values for the selected ROI recognition module are stored, the stored parameter values are used, and if there are no parameter values stored for the selected recognition module, default parameter values are set to the ROI recognition module. Then, in step S5, without waiting for the confirmation instruction from the user, the recognized ROI candidate is confirmed as the ROI, and this ROI information is set to the compression/decompression unit 106 and the write/read unit 108. Further, in this case, although a change in the ROI recognition module may be made (step S4), a selection of the region (FIG. 6, step S15), an enlargement/reduction of the region (FIG. 6, step S16), and a change in the parameter values (FIG. 6, step S17) may not be performed. - On the other hand, when the instruction (g) for automatically setting the ROI in the moving image capture mode is given, an operation identical to that performed in response to the instruction (f) for automatically setting the ROI in the still image capture mode is performed, except for the fact that the ROI is automatically set for each of the images of each of the captured frames corresponding to the captured moving image. Further, for moving image data, the image of each captured frame is independently compressed as a still image, after which the image data of all the frames are recorded on the
recording medium 110 in a motion JPEG 2000 (ISO/IEC FCD 15444-1) file format. - When the instruction (a) to perform ROI setting involving the user is given in an image playback mode, the user may intervene in setting the ROI of the still image or each of the frame images of the moving image that is compressed through lossless compression or low rate compression and recorded on the
recording medium 110. The operation performed in this case is descried below with reference to FIG. 5. - In an exemplary image playback mode, thumbnail images or lists of a plurality of images already recorded on the
recording medium 110 may be displayed on thedisplay unit 104, and the user is able to select a desired image. - When a particular image is selected, the corresponding image file is read out by the write/
read unit 108 and decompressed by the compression/decompression unit 106. Then the decompressed image data is stored in thestorage unit 102, and the image is displayed on thedisplay unit 104. Then, in step S2, the ROI is recognized by use of the selected ROI recognition module. The rest of the operation is identical to the ROI setting operation of a direct continuation of the image capture operation. However, the ROI recognition module (5) and/or ROI recognition module (6) may not be used unless AF information and/or AE information is described in the header of the corresponding image file. Also, in the case of replaying a still image, the ROI recognition module (7) and ROI recognition module (8) may not be used. In the case of replaying a moving image, the ROI recognition module (7) may be used since movement can be detected between consecutive frame images, but the ROI recognition module (8) may not be used. - If the ROI is already set in the replayed image, this ROI information will be described in the header of the corresponding image file. Thus, the
ROI control unit 120 administers thedisplay unit 104 to display the ROI on the image according to this ROI information. - In the above-described exemplary operations, the
ROI recognition unit 122 is used. Alternatively, an ROI recognition method without using theROI recognition unit 122 can also be realized. An example of such operation is described below with reference to FIG. 5. - When the above-described ROI recognition method without using the
ROI recognition unit 122 is selected in step S1 or S4, theROI control unit 120 administers the compression/decompression unit 106 to perform a lossless or a low rate compression process on the image data in step S2. The compression process may be performed on the wavelet coefficients atdecomposition level 1, for example. Then, the size (amount of codes) of each packet in each tile data is obtained by the compression/decompression unit 106, and this is compared with the determination threshold value. Then, a region (precinct) corresponding to a packet having a size greater than the determination threshold value is recognized as the ROI. In other words, according to this operation, theROI control unit 120 co-operates with the compression/decompression unit 106 to function as the ROI recognition module. Alternatively, the method for performing the ROI recognition may be set independently from theROI control unit 120. In step S6, the ROI information is set to the compression/decompression unit 106 so that the compression process is performed. Also, the ROI information is set to the write/read unit 108 so that the information is described in the header of the image file that is to be written on therecording medium 110. - Further, ROI recognition involving a user is also possible in this ROI recognition method. In this case, first the recognized ROI is displayed on the
display unit 104. Herein, the user is able to instruct selection of a region (corresponding to FIG. 6 step S15), enlargement/reduction of a region (corresponding to FIG. 6 step S16), and/or change of a packet size determination threshold value (corresponding to FIG. 6 step S17), for example. Then, when a completion instruction is input by the user, theROI control unit 120 confirms the ROI and sets the ROI information (FIG. 5 step S5). - Further the compression/
decompression unit 106 may alternatively be arranged to perform the compression process without taking the ROI into consideration, and the header of a packet having a size exceeding the packet size determination threshold value may be rewritten so that a precinct corresponding to this packet is arranged to be the ROI. - As is evident from the above descriptions, the
ROI control unit 120, theROI recognition unit 122, and a part or all of the compression/decompression unit 106 shown in FIG. 1 (and/or their functions and/or processes) may also be realized by programs implemented in a computer such as a personal computer or a microcomputer. Such programs and various recording (storage) mediums on which the programs are recorded are also included in the scope of the present invention. Also, the ROI setting apparatus and method according to the present invention is not limited to implementation in an electronic camera apparatus such as a digital camera and its method; rather, the present invention may be applied to various other types of image processing apparatuses that can record an image through image compression. - According to the present invention, an image processing apparatus such as an electronic camera apparatus is able to reduce limitations in the framing of an image while also reducing the trouble arising from a completely manual operation. Further, the present invention may be adapted for various scenes and user preferences, and is able to realize a practical ROI setting function that is applicable to various operations such as a successive capturing of still images or a capturing of a moving image.
- The present application is based on and claims the benefit of the earlier filing date of Japanese priority application No.2002-232475 filed on Aug. 9, 2002, the entire contents of which are hereby incorporated by reference.
Claims (25)
1. An ROI setting apparatus comprising:
a plurality of ROI recognition modules each for recognizing an ROI of image data according to a predetermined method and to obtain a recognition result; and
an ROI control unit adapted to select an ROI recognition module out of the plurality of ROI recognition modules and set ROI information based on the recognition result obtained by the selected ROI recognition module.
2. The ROI setting apparatus as claimed in claim 1 , wherein the ROI control unit selects the ROI recognition module according to an instruction from a user.
3. The ROI setting apparatus as claimed in claim 1 , wherein the ROI control unit selects the ROI recognition module according to a scene type selected by a user.
4. The ROI setting apparatus as claimed in claim 1 , wherein the ROI control unit sets the ROI information based on a region selected out of a plurality of regions recognized by the selected ROI recognition module, the region being selected according to an instruction from a user.
5. The ROI setting apparatus as claimed in claim 1 , wherein the ROI control unit changes a size of a region recognized by the selected ROI recognition module according to an instruction from a user.
6. The ROI setting apparatus as claimed in claim 1 , wherein the plurality of ROI recognition modules each include a recognition condition and the ROI control unit changes the recognition condition of the selected ROI recognition module according to an instruction from a user.
7. The ROI setting apparatus as claimed in claim 1 , wherein at least one of the plurality of ROI recognition modules to detect a region of the image data containing a face and using the region as a base region to recognize the ROI.
8. The ROI setting apparatus as claimed in claim 1 , wherein at least one of the plurality of ROI recognition modules to detect a region of the image data in which high frequency components are concentrated and using the region as a base region to recognize the ROI.
9. The ROI setting apparatus as claimed in claim 1 , wherein at least one of the plurality of ROI recognition modules to detect a region of the image data in which patterns having a striking contrast are concentrated and using the region as a base region to recognize the ROI.
10. The ROI setting apparatus as claimed in claim 1 , wherein at least one of the plurality of ROI recognition module to detect a region at a center portion of the image data containing an object and using the region as a base region to recognize the ROI.
11. The ROI setting apparatus as claimed in claim 1 , wherein at least one of the plurality of ROI recognition modules to use an AF evaluation region used in an image capturing operation of the image data as a base image to recognize the ROI.
12. The ROI setting apparatus as claimed in claim 1 , wherein at least one of the plurality of ROI recognition modules to use an AE evaluation region used in an image capturing operation of the image data as a base image to recognize the ROI.
13. The ROI setting apparatus as claimed in claim 1 , wherein at least one of the plurality of ROI recognition modules to detect a region of the image data in which movement occurs and using the region as a base region to recognize the ROI.
14. The ROI setting apparatus as claimed in claim 1 , wherein at least one of the plurality of ROI recognition modules to extract a region of the image data that is significantly brighter than a corresponding region of monitoring image data obtained right before an image capturing operation and using the region as a base region to recognize the ROI.
15. The ROI setting apparatus as claimed in claim 1 , wherein at least one of the plurality of ROI recognition modules to detect a high brightness region of the image data and using the region as a base region to recognize the ROI.
16. The ROI setting apparatus as claimed in claim 1 , wherein at least one of the plurality of ROI recognition modules to detect a high brightness region of the image data, subtracting from the region a high brightness region portion at a predetermined portion of the image data, and using the resulting region as a base region to recognize the ROI.
17. The ROI setting apparatus as claimed in claim 1 , wherein at least one of the plurality of ROI recognition modules to recognize the ROI based on a packet size of compressed data of the image data.
18. An electronic camera apparatus comprising:
an ROI setting apparatus having a plurality of ROI recognition modules each for recognizing an ROI of image data according to a predetermined method to obtain a recognition result, and an ROI control unit to select an ROI recognition module out of the plurality of ROI recognition modules and set ROI information based on the recognition result obtained by the selected ROI recognition module.
19. A computer readable recording medium adapted to store a program administering a computer to function as a plurality of ROI recognition modules to recognize an ROI of image data according to a predetermined ROI recognition method to obtain a recognition result, and an ROI control unit for selecting one ROI recognition module out of the plurality of ROI recognition modules and setting ROI information based on the recognition result obtained by the selected ROI recognition module, the ROI recognition module and the ROI control unit being implemented in an ROI setting apparatus.
20. An ROI setting method comprising:
selecting an ROI recognition method out of a plurality of ROI recognition methods;
recognizing an ROI of image data using the ROI recognition method to obtain a recognition result; and
setting ROI information based on the recognition result.
21. The ROI setting method as claimed in claim 20 , wherein selecting the ROI recognition method includes selecting the ROI recognition method according to an instruction from a user.
22. The ROI setting method as claimed in claim 20 , wherein selecting the ROI recognition method includes selecting an ROI recognition method according to a scene type selected by a user.
23. The ROI setting method as claimed in claim 20 , wherein setting ROI information includes setting the ROI information based on a region selected out of a plurality of regions recognized as the ROI, the region being selected according to an instruction from a user
24. The ROI setting method as claimed in claim 20 , wherein recognizing the ROI includes changing a size of a region recognized as the ROI according to an instruction from a user.
25. The ROI setting method as claimed in claim 20 , wherein each of the plurality of ROI recognition methods includes a recognition condition, and further wherein recognizing the ROI includes changing a recognition condition according to an instruction from a user.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US12/351,768 US8115821B2 (en) | 2002-08-09 | 2009-01-09 | Method and apparatus for setting a region of interest in image data |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2002-232475 | 2002-08-09 | ||
JP2002232475A JP3966461B2 (en) | 2002-08-09 | 2002-08-09 | Electronic camera device |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US12/351,768 Division US8115821B2 (en) | 2002-08-09 | 2009-01-09 | Method and apparatus for setting a region of interest in image data |
Publications (1)
Publication Number | Publication Date |
---|---|
US20040095477A1 true US20040095477A1 (en) | 2004-05-20 |
Family
ID=32017864
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US10/637,420 Abandoned US20040095477A1 (en) | 2002-08-09 | 2003-08-08 | ROI setting method and apparatus, electronic camera apparatus, program, and recording medium |
US12/351,768 Expired - Fee Related US8115821B2 (en) | 2002-08-09 | 2009-01-09 | Method and apparatus for setting a region of interest in image data |
Family Applications After (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US12/351,768 Expired - Fee Related US8115821B2 (en) | 2002-08-09 | 2009-01-09 | Method and apparatus for setting a region of interest in image data |
Country Status (3)
Country | Link |
---|---|
US (2) | US20040095477A1 (en) |
JP (1) | JP3966461B2 (en) |
CN (1) | CN1256839C (en) |
Cited By (50)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050175251A1 (en) * | 2004-02-09 | 2005-08-11 | Sanyo Electric Co., Ltd. | Image coding apparatus, image decoding apparatus, image display apparatus and image processing apparatus |
WO2005098758A1 (en) * | 2004-03-26 | 2005-10-20 | Eastman Kodak Company | Determining area of importance in an image |
US20050240104A1 (en) * | 2004-04-01 | 2005-10-27 | Medison Co., Ltd. | Apparatus and method for forming 3D ultrasound image |
US20050286741A1 (en) * | 2004-06-29 | 2005-12-29 | Sanyo Electric Co., Ltd. | Method and apparatus for coding images with different image qualities for each region thereof, and method and apparatus capable of decoding the images by adjusting the image quality |
US20060008157A1 (en) * | 2004-07-07 | 2006-01-12 | Sony Corporation | Image protection apparatus, imaging apparatus, and program |
US20060062480A1 (en) * | 2004-09-21 | 2006-03-23 | Sanyo Electric Co., Ltd. | Image processing apparatus |
US20060082841A1 (en) * | 2004-09-21 | 2006-04-20 | Olympus Corporation | Imaging apparatus |
WO2006067547A1 (en) * | 2004-12-23 | 2006-06-29 | Nokia Corporation | Method for extracting of multiple sub-windows of a scanning area by means of a digital video camera |
EP1701546A1 (en) * | 2004-04-23 | 2006-09-13 | Sumitomo Electric Industries, Ltd. | Moving picture data encoding method, decoding method, terminal device for executing them, and bi-directional interactive system |
US20060215033A1 (en) * | 2005-03-23 | 2006-09-28 | Mahowald Peter H | Setting imager parameters based on configuration patterns |
US20060245655A1 (en) * | 2005-04-28 | 2006-11-02 | Tooru Suino | Structured document code transferring method, image processing system, server apparatus and computer readable information recording medium |
US20070076957A1 (en) * | 2005-10-05 | 2007-04-05 | Haohong Wang | Video frame motion-based automatic region-of-interest detection |
GB2435141A (en) * | 2006-02-13 | 2007-08-15 | Snell & Wilcox Ltd | Adaptive re-framing of images |
EP1835719A2 (en) * | 2006-03-15 | 2007-09-19 | Canon Kabushiki Kaisha | Apparatus and method for compressions of images including a code image |
US20070230658A1 (en) * | 2004-10-29 | 2007-10-04 | Sanyo Electric Co., Ltd. | Image coding method and apparatus, and image decoding method and apparatus |
US20070242889A1 (en) * | 2006-04-12 | 2007-10-18 | Hiroyuki Sakuyama | Code processing apparatus and code processing method |
US20080225146A1 (en) * | 2007-03-16 | 2008-09-18 | Takashi Maki | Imaging apparatus and image data recording method |
US20080226186A1 (en) * | 2007-03-16 | 2008-09-18 | Taku Kodama | Image processing apparatus and method of image processing |
US20080291319A1 (en) * | 2007-04-11 | 2008-11-27 | Red.Com, Inc. | Video camera |
WO2009003885A2 (en) * | 2007-06-29 | 2009-01-08 | Thomson Licensing | Video indexing method, and video indexing device |
US20090097749A1 (en) * | 2006-03-17 | 2009-04-16 | Koninklijke Philips Electronics N. V. | Systems and methods for interactive definition of regions and volumes of interest |
EP2088774A1 (en) * | 2008-02-11 | 2009-08-12 | Vestel Elektronik Sanayi ve Ticaret A.S. | Adaptive scaling method for an entertainment system |
US20090208122A1 (en) * | 2004-10-29 | 2009-08-20 | Sanyo Electric Co., Ltd. | Image coding method and apparatus, and image decoding method and apparatus |
US20090225213A1 (en) * | 2006-10-05 | 2009-09-10 | Matsushita Electric Industrial Co., Ltd. | Luminescent display device |
US20100013963A1 (en) * | 2007-04-11 | 2010-01-21 | Red.Com, Inc. | Video camera |
US20100114746A1 (en) * | 2008-10-31 | 2010-05-06 | International Business Machines Corporation | Generating an alert based on absence of a given person in a transaction |
US20100110183A1 (en) * | 2008-10-31 | 2010-05-06 | International Business Machines Corporation | Automatically calibrating regions of interest for video surveillance |
US20100114671A1 (en) * | 2008-10-31 | 2010-05-06 | International Business Machines Corporation | Creating a training tool |
US20100118947A1 (en) * | 2007-04-04 | 2010-05-13 | Nxp B.V. | Decoder for selectively decoding predetermined data units from a coded bit stream |
US8208758B2 (en) | 2005-10-05 | 2012-06-26 | Qualcomm Incorporated | Video sensor-based automatic region-of-interest detection |
US20130101209A1 (en) * | 2010-10-29 | 2013-04-25 | Peking University | Method and system for extraction and association of object of interest in video |
US8442318B2 (en) | 2006-02-13 | 2013-05-14 | Snell Limited | Method and apparatus for modifying a moving image sequence |
CN103460254A (en) * | 2011-03-30 | 2013-12-18 | 通用电气公司 | Method and device for automatically detecting brightness based on image content |
US20140010312A1 (en) * | 2011-03-10 | 2014-01-09 | Huawei Technologies Co., Ltd. | Method and apparatus for encoding and decoding transform coefficients |
US8760540B2 (en) | 2009-01-29 | 2014-06-24 | Ricoh Company, Ltd. | Imaging device and control method of the same |
CN104093020A (en) * | 2011-03-10 | 2014-10-08 | 华为技术有限公司 | Coding method and device of transformation coefficients and decoding method and device of transformation coefficients |
CN104093018A (en) * | 2011-03-10 | 2014-10-08 | 华为技术有限公司 | Coding method and device of transformation coefficients and decoding method and device of transformation coefficients |
US20140324592A1 (en) * | 2006-10-11 | 2014-10-30 | Tagmotion Pty Limited | Method and apparatus for managing multimedia files |
US20150009364A1 (en) * | 2013-06-25 | 2015-01-08 | Glen Anderson | Management and access of media with media capture device operator perception data |
US20150370061A1 (en) * | 2013-02-05 | 2015-12-24 | Vanderbilt University | Microlens array for enhanced imaging of multiregion targets |
US9240064B2 (en) | 2011-11-09 | 2016-01-19 | Rakuten, Inc. | Image processing device, method for controlling image processing device, program, and information storage medium |
US9501160B2 (en) | 2013-09-13 | 2016-11-22 | Ricoh Company, Ltd. | Coordinate detection system and information processing apparatus |
US9521384B2 (en) | 2013-02-14 | 2016-12-13 | Red.Com, Inc. | Green average subtraction in image data |
US10917648B2 (en) | 2018-01-31 | 2021-02-09 | Canon Kabushiki Kaisha | Image processing apparatus, image processing method, and non-transitory computer-readable storage medium |
US10977491B2 (en) | 2017-03-27 | 2021-04-13 | Samsung Electronics Co., Ltd. | Device for providing information related to object in image |
CN113170044A (en) * | 2018-12-06 | 2021-07-23 | 索尼半导体解决方案公司 | Receiving apparatus and transmitting apparatus |
US11282391B2 (en) * | 2018-10-18 | 2022-03-22 | Cartica Ai Ltd. | Object detection at different illumination conditions |
US20220108457A1 (en) * | 2019-02-19 | 2022-04-07 | Sony Semiconductor Solutions Corporation | Imaging device, electronic device, and imaging method |
US11503294B2 (en) | 2017-07-05 | 2022-11-15 | Red.Com, Llc | Video image data processing in electronic devices |
US20220374156A1 (en) * | 2020-03-06 | 2022-11-24 | Hitachi, Ltd. | Data processing system and data compression method |
Families Citing this family (40)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2006014121A (en) * | 2004-06-29 | 2006-01-12 | Sanyo Electric Co Ltd | Image encoding method, image encoding apparatus, and imaging apparatus |
JP4578197B2 (en) * | 2004-09-29 | 2010-11-10 | 三洋電機株式会社 | Image display device |
JP4632417B2 (en) * | 2004-10-26 | 2011-02-16 | キヤノン株式会社 | Imaging apparatus and control method thereof |
US7440626B2 (en) * | 2004-12-02 | 2008-10-21 | Mitsubishi Electric Research Laboratories, Inc. | Image transcoding |
US7506817B2 (en) * | 2004-12-14 | 2009-03-24 | Ricoh Co., Ltd. | Location of machine readable codes in compressed representations |
JP4720255B2 (en) * | 2005-03-31 | 2011-07-13 | カシオ計算機株式会社 | Camera device, photographing method and photographing program |
JP4720252B2 (en) * | 2005-03-31 | 2011-07-13 | カシオ計算機株式会社 | Camera device, imaging method, and imaging program |
JP4934983B2 (en) * | 2005-03-31 | 2012-05-23 | カシオ計算機株式会社 | Camera device, photographing method and photographing program |
JP2006287517A (en) * | 2005-03-31 | 2006-10-19 | Casio Comput Co Ltd | Camera apparatus, photographing method, and photographing program |
JP4693522B2 (en) * | 2005-06-29 | 2011-06-01 | キヤノン株式会社 | Imaging device |
JP2007157063A (en) | 2005-12-08 | 2007-06-21 | Sony Corp | Image processor, image processing method and computer program |
JP2008052566A (en) * | 2006-08-25 | 2008-03-06 | Canon Inc | Image processor and image processing method |
JP2008245033A (en) * | 2007-03-28 | 2008-10-09 | Institute Of National Colleges Of Technology Japan | Method of controlling depth of field, image processing device, program, and recording medium |
JP5464799B2 (en) | 2007-11-16 | 2014-04-09 | キヤノン株式会社 | Image processing apparatus, image processing method, and program |
JP5116513B2 (en) * | 2008-03-10 | 2013-01-09 | キヤノン株式会社 | Image display apparatus and control method thereof |
KR101436326B1 (en) | 2008-07-31 | 2014-09-01 | 삼성전자주식회사 | Digital photographing apparatus, method for controlling the same, and recording medium storing program to implement the method |
JP5116608B2 (en) * | 2008-08-20 | 2013-01-09 | キヤノン株式会社 | Information processing apparatus, control method, and program |
JP2010055194A (en) | 2008-08-26 | 2010-03-11 | Sony Corp | Image processing device and method, learning device and method, and program |
KR101520068B1 (en) | 2008-12-16 | 2015-05-13 | 삼성전자 주식회사 | Apparatus and method of blending multiple image |
JP5285632B2 (en) * | 2009-01-26 | 2013-09-11 | パナソニック株式会社 | Moving image processing apparatus, moving image processing method, and imaging apparatus |
JP2010256536A (en) * | 2009-04-23 | 2010-11-11 | Sharp Corp | Image processing device and image display device |
AU2009357597B2 (en) * | 2009-12-30 | 2015-11-05 | Nokia Technologies Oy | Methods and apparatuses for facilitating content-based image retrieval |
JP2011221519A (en) * | 2010-03-25 | 2011-11-04 | Panasonic Corp | Imaging device |
JP5569206B2 (en) * | 2010-07-15 | 2014-08-13 | ソニー株式会社 | Image processing apparatus and method |
JP5025804B2 (en) * | 2011-01-31 | 2012-09-12 | キヤノン株式会社 | Imaging device |
JP5870533B2 (en) * | 2011-08-09 | 2016-03-01 | 株式会社リコー | Imaging apparatus and imaging method |
US9361718B2 (en) * | 2011-09-08 | 2016-06-07 | Intel Corporation | Interactive screen viewing |
TW201329783A (en) * | 2012-01-05 | 2013-07-16 | Pixart Imaging Inc | Remote device and remote control system |
KR101382873B1 (en) * | 2012-06-29 | 2014-04-08 | 엘지이노텍 주식회사 | Forward Collision Warning System and Forward Collision Warning Method |
CN103179331B (en) * | 2013-04-18 | 2017-02-08 | 华中科技大学 | Scanning sampling and image processing method of fast imaging |
KR101458944B1 (en) * | 2013-05-31 | 2014-11-10 | 한국산업은행 | Apparatus and method for specify the speaker coordinate using focus |
CN104079934B (en) * | 2014-07-14 | 2017-02-15 | 武汉大学 | Method for extracting regions of interest in real-time video communication |
US20170054897A1 (en) * | 2015-08-21 | 2017-02-23 | Samsung Electronics Co., Ltd. | Method of automatically focusing on region of interest by an electronic device |
US11715556B2 (en) | 2016-08-11 | 2023-08-01 | DiamondFox Enterprises, LLC | Handheld arthropod detection device |
US10496893B2 (en) | 2016-08-11 | 2019-12-03 | DiamondFox Enterprises, LLC | Handheld arthropod detection device |
JP7056564B2 (en) | 2016-08-23 | 2022-04-19 | 日本電気株式会社 | Video processing equipment, video processing methods and programs |
KR101827168B1 (en) * | 2016-11-04 | 2018-02-08 | 재단법인대구경북과학기술원 | Device and method for outputting face syntheses contents |
JP6882136B2 (en) * | 2017-10-12 | 2021-06-02 | 日本メジフィジックス株式会社 | Image processing equipment, image processing methods and programs |
CN109995999A (en) * | 2019-03-14 | 2019-07-09 | Oppo广东移动通信有限公司 | Scene recognition method, device, electronic equipment and storage medium |
US11576364B2 (en) | 2020-03-30 | 2023-02-14 | Cnh Industrial America Llc | System and method for determining agricultural vehicle guidance quality based on a crop row boundary consistency parameter |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040004670A1 (en) * | 2002-03-14 | 2004-01-08 | Canon Kabushiki Kaisha | Image pickup apparatus having auto-focus control and image pickup method |
US20040032526A1 (en) * | 1997-07-15 | 2004-02-19 | Silverbrook Research Pty Ltd | Method of processing digital image to correct for flash effects |
Family Cites Families (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2000041694A (en) | 1990-03-08 | 2000-02-15 | Hayashibara Biochem Lab Inc | Substance having high lactosucrose, its production and use |
JP3252941B2 (en) * | 1994-11-29 | 2002-02-04 | 日本電信電話株式会社 | Image segmentation recognition device |
US5889582A (en) * | 1997-03-10 | 1999-03-30 | Virtek Vision Corporation | Image-directed active range finding system |
JPH11294343A (en) | 1998-04-14 | 1999-10-26 | Mitsubishi Motors Corp | Control device of electromagnetic type pump |
JP2000209590A (en) * | 1999-01-11 | 2000-07-28 | Canon Inc | Image encoder, image encoding method, storage medium and image pickup device |
JP4331314B2 (en) * | 1999-04-12 | 2009-09-16 | オリンパス株式会社 | Single-lens reflex type electronic imaging device |
JP3810943B2 (en) * | 1999-05-06 | 2006-08-16 | 株式会社東芝 | Image processing apparatus, image processing method, and recording medium recording image processing program |
JP2000358183A (en) * | 1999-06-14 | 2000-12-26 | Canon Inc | Image processing device and its method |
US6490319B1 (en) * | 1999-06-22 | 2002-12-03 | Intel Corporation | Region of interest video coding |
JP2001036901A (en) * | 1999-07-15 | 2001-02-09 | Canon Inc | Device and method for processing image and memory medium |
JP4294805B2 (en) * | 1999-08-10 | 2009-07-15 | 富士フイルム株式会社 | Image processing apparatus, image processing method, and recording medium |
JP2001119696A (en) * | 1999-10-20 | 2001-04-27 | Canon Inc | Method and device for encoding image |
JP2001145101A (en) * | 1999-11-12 | 2001-05-25 | Mega Chips Corp | Human image compressing device |
JP2001230947A (en) * | 2000-02-18 | 2001-08-24 | Canon Inc | Device and method for processing image |
JP3758452B2 (en) * | 2000-02-28 | 2006-03-22 | コニカミノルタビジネステクノロジーズ株式会社 | RECORDING MEDIUM, IMAGE PROCESSING DEVICE, AND IMAGE PROCESSING METHOD |
JP2002064790A (en) * | 2000-05-31 | 2002-02-28 | Canon Inc | Image processor, its method program code and storage medium |
JP4686854B2 (en) * | 2000-12-08 | 2011-05-25 | 株式会社ニコン | Image encoding device, electronic camera, and recording medium for image encoding program |
JP4517504B2 (en) * | 2000-12-22 | 2010-08-04 | 株式会社ニコン | Image encoding apparatus, electronic camera, and recording medium |
-
2002
- 2002-08-09 JP JP2002232475A patent/JP3966461B2/en not_active Expired - Lifetime
-
2003
- 2003-08-08 US US10/637,420 patent/US20040095477A1/en not_active Abandoned
- 2003-08-09 CN CNB03158683XA patent/CN1256839C/en not_active Expired - Lifetime
-
2009
- 2009-01-09 US US12/351,768 patent/US8115821B2/en not_active Expired - Fee Related
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040032526A1 (en) * | 1997-07-15 | 2004-02-19 | Silverbrook Research Pty Ltd | Method of processing digital image to correct for flash effects |
US20040004670A1 (en) * | 2002-03-14 | 2004-01-08 | Canon Kabushiki Kaisha | Image pickup apparatus having auto-focus control and image pickup method |
Cited By (103)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8005309B2 (en) | 2004-02-09 | 2011-08-23 | Sanyo Electric Co., Ltd. | Image coding apparatus, image decoding apparatus, image display apparatus and image processing apparatus |
US20050175251A1 (en) * | 2004-02-09 | 2005-08-11 | Sanyo Electric Co., Ltd. | Image coding apparatus, image decoding apparatus, image display apparatus and image processing apparatus |
WO2005098758A1 (en) * | 2004-03-26 | 2005-10-20 | Eastman Kodak Company | Determining area of importance in an image |
US20050240104A1 (en) * | 2004-04-01 | 2005-10-27 | Medison Co., Ltd. | Apparatus and method for forming 3D ultrasound image |
US7507204B2 (en) * | 2004-04-01 | 2009-03-24 | Medison Co., Ltd. | Apparatus and method for forming 3D ultrasound image |
US7983497B2 (en) | 2004-04-23 | 2011-07-19 | Sumitomo Electric Industries, Ltd. | Coding method for motion-image data, decoding method, terminal equipment executing these, and two-way interactive system |
EP1701546A1 (en) * | 2004-04-23 | 2006-09-13 | Sumitomo Electric Industries, Ltd. | Moving picture data encoding method, decoding method, terminal device for executing them, and bi-directional interactive system |
EP1701546A4 (en) * | 2004-04-23 | 2010-09-15 | Sumitomo Electric Industries | Moving picture data encoding method, decoding method, terminal device for executing them, and bi-directional interactive system |
US20100135587A1 (en) * | 2004-06-29 | 2010-06-03 | Sanyo Electric Co., Ltd. | Method and apparatus for coding images with different image qualities for each region thereof, and method and apparatus capable of decoding the images by adjusting the image quality |
US20050286741A1 (en) * | 2004-06-29 | 2005-12-29 | Sanyo Electric Co., Ltd. | Method and apparatus for coding images with different image qualities for each region thereof, and method and apparatus capable of decoding the images by adjusting the image quality |
US7720295B2 (en) | 2004-06-29 | 2010-05-18 | Sanyo Electric Co., Ltd. | Method and apparatus for coding images with different image qualities for each region thereof, and method and apparatus capable of decoding the images by adjusting the image quality |
US20060008157A1 (en) * | 2004-07-07 | 2006-01-12 | Sony Corporation | Image protection apparatus, imaging apparatus, and program |
US20060082841A1 (en) * | 2004-09-21 | 2006-04-20 | Olympus Corporation | Imaging apparatus |
US7542613B2 (en) | 2004-09-21 | 2009-06-02 | Sanyo Electric Co., Ltd. | Image processing apparatus |
US20060062480A1 (en) * | 2004-09-21 | 2006-03-23 | Sanyo Electric Co., Ltd. | Image processing apparatus |
US8150173B2 (en) | 2004-10-29 | 2012-04-03 | Sanyo Electric Co., Ltd. | Image coding method and apparatus, and image decoding method and apparatus |
US8208738B2 (en) | 2004-10-29 | 2012-06-26 | Sanyo Electric Co., Ltd. | Image coding method and apparatus, and image decoding method and apparatus |
US20070230658A1 (en) * | 2004-10-29 | 2007-10-04 | Sanyo Electric Co., Ltd. | Image coding method and apparatus, and image decoding method and apparatus |
US20090208122A1 (en) * | 2004-10-29 | 2009-08-20 | Sanyo Electric Co., Ltd. | Image coding method and apparatus, and image decoding method and apparatus |
US20080075373A1 (en) * | 2004-10-29 | 2008-03-27 | Sanyo Electric Co., Ltd. | Image Coding Method and Apparatus, and Image Decoding Method and Apparatus |
WO2006067547A1 (en) * | 2004-12-23 | 2006-06-29 | Nokia Corporation | Method for extracting of multiple sub-windows of a scanning area by means of a digital video camera |
US20080225130A1 (en) * | 2004-12-23 | 2008-09-18 | Nokia Corporation | Method for Extracting of Multiple Sub-Windows of a Scanning Area by Means of a Digital Video Camera |
US7733375B2 (en) | 2005-03-23 | 2010-06-08 | Marvell International Technology Ltd. | Setting imager parameters based on configuration patterns |
US20060215033A1 (en) * | 2005-03-23 | 2006-09-28 | Mahowald Peter H | Setting imager parameters based on configuration patterns |
US20060245655A1 (en) * | 2005-04-28 | 2006-11-02 | Tooru Suino | Structured document code transferring method, image processing system, server apparatus and computer readable information recording medium |
US7912324B2 (en) | 2005-04-28 | 2011-03-22 | Ricoh Company, Ltd. | Orderly structured document code transferring method using character and non-character mask blocks |
US8019170B2 (en) | 2005-10-05 | 2011-09-13 | Qualcomm, Incorporated | Video frame motion-based automatic region-of-interest detection |
US8208758B2 (en) | 2005-10-05 | 2012-06-26 | Qualcomm Incorporated | Video sensor-based automatic region-of-interest detection |
US20070076957A1 (en) * | 2005-10-05 | 2007-04-05 | Haohong Wang | Video frame motion-based automatic region-of-interest detection |
US8442318B2 (en) | 2006-02-13 | 2013-05-14 | Snell Limited | Method and apparatus for modifying a moving image sequence |
GB2435141A (en) * | 2006-02-13 | 2007-08-15 | Snell & Wilcox Ltd | Adaptive re-framing of images |
EP1835719A3 (en) * | 2006-03-15 | 2007-10-17 | Canon Kabushiki Kaisha | Apparatus and method for compressions of images including a code image |
US8139876B2 (en) | 2006-03-15 | 2012-03-20 | Canon Kabushiki Kaisha | Image processing apparatus, control method for image processing apparatus, program, and storage medium |
US8300957B2 (en) | 2006-03-15 | 2012-10-30 | Canon Kabushiki Kaisha | Image processing apparatus, control method for image processing apparatus, program, and storage medium |
US20070217697A1 (en) * | 2006-03-15 | 2007-09-20 | Canon Kabushiki Kaisha | Image processing apparatus, control method for image processing apparatus, program, and storage medium |
US20070217696A1 (en) * | 2006-03-15 | 2007-09-20 | Canon Kabushiki Kaisha | Image processing apparatus, control method for image processing apparatus, program, and storage medium |
EP1835719A2 (en) * | 2006-03-15 | 2007-09-19 | Canon Kabushiki Kaisha | Apparatus and method for compressions of images including a code image |
US20090097749A1 (en) * | 2006-03-17 | 2009-04-16 | Koninklijke Philips Electronics N. V. | Systems and methods for interactive definition of regions and volumes of interest |
US7865028B2 (en) | 2006-04-12 | 2011-01-04 | Ricoh Company, Ltd. | Code processing apparatus and code processing method |
US20070242889A1 (en) * | 2006-04-12 | 2007-10-18 | Hiroyuki Sakuyama | Code processing apparatus and code processing method |
US20090225213A1 (en) * | 2006-10-05 | 2009-09-10 | Matsushita Electric Industrial Co., Ltd. | Luminescent display device |
AU2017200109B2 (en) * | 2006-10-11 | 2019-02-14 | Tagmotion Pty Ltd | Method and Apparatus for Managing Multimedia Files |
US20140324592A1 (en) * | 2006-10-11 | 2014-10-30 | Tagmotion Pty Limited | Method and apparatus for managing multimedia files |
US10795924B2 (en) * | 2006-10-11 | 2020-10-06 | Tagmotion Pty Limited | Method and apparatus for managing multimedia files |
US20080226186A1 (en) * | 2007-03-16 | 2008-09-18 | Taku Kodama | Image processing apparatus and method of image processing |
US20080225146A1 (en) * | 2007-03-16 | 2008-09-18 | Takashi Maki | Imaging apparatus and image data recording method |
US8135223B2 (en) | 2007-03-16 | 2012-03-13 | Ricoh Company, Ltd. | Image processing apparatus and method of image processing |
US20100118947A1 (en) * | 2007-04-04 | 2010-05-13 | Nxp B.V. | Decoder for selectively decoding predetermined data units from a coded bit stream |
US8902992B2 (en) * | 2007-04-04 | 2014-12-02 | Entropic Communications, Inc. | Decoder for selectively decoding predetermined data units from a coded bit stream |
US9245314B2 (en) | 2007-04-11 | 2016-01-26 | Red.Com, Inc. | Video camera |
US20100013963A1 (en) * | 2007-04-11 | 2010-01-21 | Red.Com, Inc. | Video camera |
US8174560B2 (en) | 2007-04-11 | 2012-05-08 | Red.Com, Inc. | Video camera |
US20100265367A1 (en) * | 2007-04-11 | 2010-10-21 | Red.Com, Inc. | Video camera |
US9436976B2 (en) | 2007-04-11 | 2016-09-06 | Red.Com, Inc. | Video camera |
US8237830B2 (en) | 2007-04-11 | 2012-08-07 | Red.Com, Inc. | Video camera |
US9230299B2 (en) | 2007-04-11 | 2016-01-05 | Red.Com, Inc. | Video camera |
US9596385B2 (en) | 2007-04-11 | 2017-03-14 | Red.Com, Inc. | Electronic apparatus |
US8358357B2 (en) | 2007-04-11 | 2013-01-22 | Red.Com, Inc. | Video camera |
US9019393B2 (en) | 2007-04-11 | 2015-04-28 | Red.Com, Inc. | Video processing system and method |
US9787878B2 (en) | 2007-04-11 | 2017-10-10 | Red.Com, Llc | Video camera |
US8878952B2 (en) | 2007-04-11 | 2014-11-04 | Red.Com, Inc. | Video camera |
US8872933B2 (en) | 2007-04-11 | 2014-10-28 | Red.Com, Inc. | Video camera |
US20080291319A1 (en) * | 2007-04-11 | 2008-11-27 | Red.Com, Inc. | Video camera |
US7830967B1 (en) | 2007-04-11 | 2010-11-09 | Red.Com, Inc. | Video camera |
US9792672B2 (en) | 2007-04-11 | 2017-10-17 | Red.Com, Llc | Video capture devices and methods |
WO2009003885A2 (en) * | 2007-06-29 | 2009-01-08 | Thomson Licensing | Video indexing method, and video indexing device |
WO2009003885A3 (en) * | 2007-06-29 | 2009-03-26 | Thomson Licensing | Video indexing method, and video indexing device |
EP2088774A1 (en) * | 2008-02-11 | 2009-08-12 | Vestel Elektronik Sanayi ve Ticaret A.S. | Adaptive scaling method for an entertainment system |
US8612286B2 (en) | 2008-10-31 | 2013-12-17 | International Business Machines Corporation | Creating a training tool |
US20100114746A1 (en) * | 2008-10-31 | 2010-05-06 | International Business Machines Corporation | Generating an alert based on absence of a given person in a transaction |
US8429016B2 (en) | 2008-10-31 | 2013-04-23 | International Business Machines Corporation | Generating an alert based on absence of a given person in a transaction |
US8345101B2 (en) * | 2008-10-31 | 2013-01-01 | International Business Machines Corporation | Automatically calibrating regions of interest for video surveillance |
US20100110183A1 (en) * | 2008-10-31 | 2010-05-06 | International Business Machines Corporation | Automatically calibrating regions of interest for video surveillance |
US20100114671A1 (en) * | 2008-10-31 | 2010-05-06 | International Business Machines Corporation | Creating a training tool |
US8760540B2 (en) | 2009-01-29 | 2014-06-24 | Ricoh Company, Ltd. | Imaging device and control method of the same |
US20130101209A1 (en) * | 2010-10-29 | 2013-04-25 | Peking University | Method and system for extraction and association of object of interest in video |
US20140010312A1 (en) * | 2011-03-10 | 2014-01-09 | Huawei Technologies Co., Ltd. | Method and apparatus for encoding and decoding transform coefficients |
US9571836B2 (en) * | 2011-03-10 | 2017-02-14 | Huawei Technologies Co., Ltd. | Method and apparatus for encoding and decoding with multiple transform coefficients sub-blocks |
CN104093020A (en) * | 2011-03-10 | 2014-10-08 | 华为技术有限公司 | Coding method and device of transformation coefficients and decoding method and device of transformation coefficients |
US10165305B2 (en) | 2011-03-10 | 2018-12-25 | Huawei Technologies Co., Ltd. | Encoding and decoding transform coefficient sub-blocks in same predetermine order |
CN104093018A (en) * | 2011-03-10 | 2014-10-08 | 华为技术有限公司 | Coding method and device of transformation coefficients and decoding method and device of transformation coefficients |
CN103460254A (en) * | 2011-03-30 | 2013-12-18 | 通用电气公司 | Method and device for automatically detecting brightness based on image content |
US9330333B2 (en) | 2011-03-30 | 2016-05-03 | General Electric Company | Method and apparatus for image content-based automatic brightness detection |
US9240064B2 (en) | 2011-11-09 | 2016-01-19 | Rakuten, Inc. | Image processing device, method for controlling image processing device, program, and information storage medium |
US10036877B2 (en) * | 2013-02-05 | 2018-07-31 | Vanderbilt University | Microlens array for enhanced imaging of multiregion targets |
US20150370061A1 (en) * | 2013-02-05 | 2015-12-24 | Vanderbilt University | Microlens array for enhanced imaging of multiregion targets |
US10582168B2 (en) | 2013-02-14 | 2020-03-03 | Red.Com, Llc | Green image data processing |
US9716866B2 (en) | 2013-02-14 | 2017-07-25 | Red.Com, Inc. | Green image data processing |
US9521384B2 (en) | 2013-02-14 | 2016-12-13 | Red.Com, Inc. | Green average subtraction in image data |
US20150009364A1 (en) * | 2013-06-25 | 2015-01-08 | Glen Anderson | Management and access of media with media capture device operator perception data |
US9501160B2 (en) | 2013-09-13 | 2016-11-22 | Ricoh Company, Ltd. | Coordinate detection system and information processing apparatus |
US10977491B2 (en) | 2017-03-27 | 2021-04-13 | Samsung Electronics Co., Ltd. | Device for providing information related to object in image |
US11503294B2 (en) | 2017-07-05 | 2022-11-15 | Red.Com, Llc | Video image data processing in electronic devices |
US11818351B2 (en) | 2017-07-05 | 2023-11-14 | Red.Com, Llc | Video image data processing in electronic devices |
US10917648B2 (en) | 2018-01-31 | 2021-02-09 | Canon Kabushiki Kaisha | Image processing apparatus, image processing method, and non-transitory computer-readable storage medium |
US11282391B2 (en) * | 2018-10-18 | 2022-03-22 | Cartica Ai Ltd. | Object detection at different illumination conditions |
US20230239570A1 (en) * | 2018-12-06 | 2023-07-27 | Sony Semiconductor Solutions Corporation | Reception apparatus and transmission apparatus |
US11606500B2 (en) * | 2018-12-06 | 2023-03-14 | Sony Semiconductor Solutions Corporation | Reception apparatus and transmission apparatus |
CN113170044A (en) * | 2018-12-06 | 2021-07-23 | 索尼半导体解决方案公司 | Receiving apparatus and transmitting apparatus |
US11924546B2 (en) * | 2018-12-06 | 2024-03-05 | Sony Semiconductor Solutions Corporation | Reception apparatus and transmission apparatus |
US20220108457A1 (en) * | 2019-02-19 | 2022-04-07 | Sony Semiconductor Solutions Corporation | Imaging device, electronic device, and imaging method |
US20220374156A1 (en) * | 2020-03-06 | 2022-11-24 | Hitachi, Ltd. | Data processing system and data compression method |
US11842055B2 (en) * | 2020-03-06 | 2023-12-12 | Hitachi, Ltd. | Data processing system and data compression method |
Also Published As
Publication number | Publication date |
---|---|
CN1496110A (en) | 2004-05-12 |
US8115821B2 (en) | 2012-02-14 |
JP2004072655A (en) | 2004-03-04 |
CN1256839C (en) | 2006-05-17 |
JP3966461B2 (en) | 2007-08-29 |
US20090122164A1 (en) | 2009-05-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US8115821B2 (en) | Method and apparatus for setting a region of interest in image data | |
US20060045381A1 (en) | Image processing apparatus, shooting apparatus and image display apparatus | |
US7359549B2 (en) | Imaging device, image processing method, and recording medium | |
JP4973098B2 (en) | Image processing apparatus, image processing method, and program | |
JP4406640B2 (en) | Method for creating compressed image data file, image data compression apparatus and photographing apparatus | |
USRE42978E1 (en) | Image capturing device | |
US20040212843A1 (en) | Image processing method, image processing apparatus, electronic camera and computer-readable storage medium | |
US8350920B2 (en) | Image capturing apparatus, image capturing method, image processing apparatus, image processing method, and program capable of hiding desired character information and restoring the hidden character information | |
US8009924B2 (en) | Method and apparatus for recording image data | |
JPH053550A (en) | Device and method for encoding image data | |
US7333662B2 (en) | Image coding and decoding using intermediate images | |
US20100007774A1 (en) | Image processor | |
WO2005004488A1 (en) | Electronic camera | |
JP4822396B2 (en) | Image enhancement device | |
US20060228034A1 (en) | Digital diaphragm system | |
JP2000358183A (en) | Image processing device and its method | |
JP2008278466A (en) | Image processing apparatus and imaging apparatus mounting the same, and image processing method | |
JP2006074114A (en) | Image processing apparatus and imaging apparatus | |
TWI390959B (en) | Video signal processing device, video signal processing method and video signal processing program | |
JP2001333430A (en) | Image processing unit, method, and computer-readable storage medium | |
JP2000209590A (en) | Image encoder, image encoding method, storage medium and image pickup device | |
JP4129913B2 (en) | Image processing apparatus and image processing method | |
JP4742642B2 (en) | Image processing apparatus, printing apparatus, image processing method, and image processing program | |
JP2994437B2 (en) | Digital electronic still camera and image attribute determination method | |
JP2004032105A (en) | Image processing apparatus, image processing system, image processing method, storage medium, and program |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: RICOH COMPANY, LTD., JAPAN Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:MAKI, TAKASHI;IKEBE, KEIICHI;SAKUYAMA, HIROYUKI;AND OTHERS;REEL/FRAME:014869/0492;SIGNING DATES FROM 20031119 TO 20031126 |
|
STCB | Information on status: application discontinuation |
Free format text: ABANDONED -- FAILURE TO RESPOND TO AN OFFICE ACTION |