CN101976441A - Method for extracting Sobel operator filtering profile for representing fabric texture and fractal detail mixed characteristic vector - Google Patents

Abstract

The invention relates to a method for extracting a Sobel operator filtering profile for representing fabric texture and a fractal detail mixed characteristic vector, which comprises the following steps of: firstly, taking a group of gray scale statistics with respective unified calculation mode as profile characteristics on the basis of carrying out horizontal and vertical Sobel operator filtering on an original fabric image respectively; calculating the fractal dimension of each child window comprising a lateral basic cycle period or longitudinal basic cycle period in the original image based on the traversal method principle; selecting two fractal dimension extreme limits for reflecting lateral detail information and two fractal dimension extreme limits for reflecting longitudinal detail information as detail characteristics for representing the fabric texture; and combing the two Sobel operator filtering profile characteristics and four fractal detail characteristics to form a mixed characteristic vector. The mixed characteristic vector has high complementarity among all characteristics, combines the profile information and the detail information of the texture, also combines the lateral information and the longitudinal information of the texture and can describe the characteristics of the fabric texture comprehensively in detail.

Description

A kind ofly be used to characterize cloth textured Sobel operator filtering general picture and fractal details composite character vector extracting method

Technical field

The invention belongs to Digital Image Processing and area of pattern recognition, particularly a kind ofly be used to characterize cloth textured Sobel operator filtering general picture and fractal details composite character vector extracting method.

Background technology

Can realize cloth textured parameter estimation, Texture classification, appearance of fabrics evaluation, Defect Detection or the like purpose by cloth textured characterization technique.Any cloth textured important information that all comprises two aspects, i.e. profile information and detailed information.Profile information provides overall rough structure and gray scale impression for human eye or machine vision, and detailed information then provides local meticulous structure and gray scale impression.Therefore, be comprehensively and characterize texture structure meticulously, reflect texture feature to greatest extent, when feature extraction, just must take into account the general picture and the detailed information of texture.For the ease of statement, the application plans those features that mainly reflect profile information and is called the general picture feature, and those features that mainly reflect detailed information are called minutia.Obviously, general picture feature and minutia emphasize particularly on different fields, and have great complementarity.The present invention is intended to discuss the cloth textured characterizing method based on Sobel operator filtering general picture feature and fractal minutia.

Than euclidean geometry, fractal geometry can provide better method when describing or generating natural things with self-similarity or class natural things, thereby extensively are used in the simulation of pattern-recognition, image and emulation or the like numerous areas.Self-similarity is one of central concept of fractal theory, and the notion of it and dimension is closely related.The object that fractal geometry are described has the self similarity on the statistical significance, and it is one of characteristic parameter of the most normal use when carrying out graphical analysis with fractal theory that self-similarity characterizes FRACTAL DIMENSION with FRACTAL DIMENSION.Fractal characteristic particularly fractal dimension can be portrayed coarse texture degree and complexity preferably, thus in practices such as Texture classification, identification as tolerance feature be rational.Wherein box counting dimension simple owing to notion, calculate the easy the most general a kind of fractal dimension of use that becomes.

For ease of explanation invention main points, be necessary box counting dimension and Sobel operator Principle of Filtering are done simple the introduction.

If

Be non-NULL bounded aggregate arbitrarily, with N (δ, F) expression cover collection F required diameter be to the maximum δ the minimal number of collection, then the box dimension definition of F is

$D_B\left(F\right)=\underset{\mathrm{\δ}\→0}{\lim }\frac{\log N(\mathrm{\δ},F)}{-\log \mathrm{\δ}}$

Note, used δ-covering is still a general collection class in the definition, in this patent collection F refer in particular to into textile image when the vertical, horizontal projection, by the gradation of image one dimension time series that each is capable, each row pixel grey scale adds up and get the average gained, it also is the curve of each each row pixel grey scale Change in Mean of row of a presentation video, (δ, F) the required length of side of expression covering F is the minimum number of squares of δ to N, notes by abridging into N (δ).D _B(F) brief note is D.

During seasonal effect in time series meter box dimension of actual estimation, because this sequence is a curve, horizontal ordinate is the position of each point in the sequence, and ordinate is the sequential value of each point correspondence, need remove to cover fully this curve and add up N (δ) with the grid that is of a size of δ * δ.From the definition of box counting dimension as can be known, logN (δ) ∞ Dlog (1/ δ), this shows, and some is straight line to (log (1/ δ), logN (δ)) asymptotic line in δ → 0 o'clock, and its slope is D.It is right that thereby change δ size can obtain a plurality of above-mentioned points, goes out respective straight by least square fitting then.The slope of this straight line is the box counting dimension of being asked.

Consider that woven fabric is by vertically being interwoven mutually through weft yarn, its image is a kind of typical texture image, and therefore available fractal characteristic characterizes cloth textured.People such as Conci (1998) adopt difference meter box method to extract cloth textured FRACTAL DIMENSION and standard deviation is used for characterizing cloth textured as characteristic parameter and detect fabric defects.People such as Xu Zengbo (2000) carry out at cloth textured image on the basis of Wold model analysis, with ask in the FRACTAL DIMENSION process whole fractal characteristic curve as characterizing cloth textured feature, carried out the fabric defects detection.People such as Wen (2002) adopt this fractal parameter of Hurst coefficient of estimating textile image based on the Fourier domain maximal possibility estimation operator of fractal Brown motion, detect fault with this as characterizing cloth textured characteristic parameter.People such as Yang Yan (2007) have extracted an overall FRACTAL DIMENSION feature and have realized objective evaluation to the fabric crape effect from the crepe fabric image.Go on foot the red firm people of grade (2007) in order to overcome the limitation of single fractal characteristic, a kind of many fractal characteristic vector extracting method have been proposed, the more relevant research on the defect detection effect of this method has had significantly improvement, but because a plurality of fractal characteristic vectors that extracted all are general picture features of reflection global information, thereby be unsuitable for detecting a lot of local faults.In the patent of " based on square and fractal texture classifying method " (2006), the researcher is the second moment of computed image at first, produce the moment characteristics image, again original image piece and moment characteristics image are estimated its fractal dimension, fractal dimension with original image piece and six moment characteristics images forms proper vector at last, carries out cloth textured classification as the input of support vector machine.

The Sobel operator is one of operator in the Flame Image Process, mainly as rim detection.Technically, it is a discreteness difference operator, is used for the approximate value of gradient of arithmograph image brightness function.Use this operator in any point of image, will produce corresponding gradient vector.The Sobel operator has two, a detection level edge, another detection of vertical edge.The Sobel operator image space utilize two 3 * 3 direction template in other words in convolution kernel and the image each point carry out the neighborhood convolution and finish rim detection, one of them strengthens the horizontal direction edge of image by the almost vertical direction gradient this both direction template, and another then strengthens the vertical direction edge of image by the level of approximation direction gradient.Sobel level and vertical edge strengthen template and are respectively

$T_x=\left(\begin{array}{ccc}1& 2& 1\\ 0& 0& 0\\ -1& -2& -1\end{array}\right)$

With $T_y=\left(\begin{array}{ccc}1& 0& -1\\ 2& 0& -2\\ 1& 0& -1\end{array}\right)$

At cloth textured Sobel operator representational field, do not see relevant domestic article or patent report as yet.In order to detect fabric crapand flaw, the Jasper of the U.S. and Potapalli adopt Sobel horizontal filtering operator that textile image has been carried out Filtering Processing, but only extracted the filtered edge image sectional view of Sobel, do not carry out more deep texture phenetic analysis, and only relate to a Sobel filter operator.In order to detect fabric defects, Lane has proposed the texture characterizing method that a kind of Sobel of employing operator and mathematical morphology combine in the American National patent of its application, its method is, at first original image is carried out Sobel level and vertical filtering, then two filtering images are merged, then this image binaryzation is handled, then carried out the mathematical morphology of binary image and handle, at last with the feature of frontier point as the sign texture.This report does not have to consider with the foundation of basic length of the cycle of texture cycle as feature extraction, the choosing method of binary-state threshold is not described, the single feature of being extracted also only relates to the frontier point pixel quantity, and clearly do not define the implication of frontier point, do not consider the distribution situation of frontier point in image.

The cloth textured characterizing method that above-mentioned existing document or patent relate to all is the extraction that is confined to global characteristics to the sign of cloth textured information, fail to take into account cloth textured general picture and detailed information, thereby can not be comprehensively and characterize cloth textured essential characteristic meticulously.In addition, above-mentioned Sobel operator texture characterizing method principal feature is that texture image must be chosen certain threshold value to realize the binaryzation of image after Sobel operator Filtering Processing.Two major defects are arranged like this: the one, choose the thing that optimal threshold is a difficulty at different texture; The 2nd, image is after binary conversion treatment, and a large amount of grayscale transition information are lost, only remaining complete black and complete two white value informations, and pending texture image has 256 gray levels usually.Therefore, the comparatively loaded down with trivial details and feature that extract on this basis of above-mentioned disposal route can not realize the more abundant properer sign of texture.And above-mentioned document or patent be in cloth textured fractal characteristic characterizes, and have following shortcoming: 1, feature is directly extracted on the two dimensional image basis, and calculated amount is big; 2, the fractal characteristic that is extracted only can be portrayed the global information of texture, can not carefully profoundly characterize cloth textured detailed information; 3, underuse cloth textured intrinsic longitude and latitude orientation characteristics during feature extraction to improve the stability of feature; 4, Feature Extraction underuse fabric through the intrinsic regular round-robin characteristics of weft yarn to improve the accuracy and the stability of feature.

Summary of the invention

The invention belongs to Digital Image Processing and area of pattern recognition, particularly a kind ofly be used to characterize cloth textured Sobel operator filtering general picture and fractal details composite character vector extracting method.At first on the basis of the source textile image being carried out level and vertical Sobel operator Filtering Processing respectively, from two kinds of corresponding filtering images separately one group of gray-scale statistical amount of account form unanimity as the general picture feature; Simultaneously calculate in the original image fractal dimension of each subwindow that comprises a laterally basic cycle period according to traversal method principle and each comprises the fractal dimension of the subwindow of a vertically basic cycle period, the fractal dimension extreme values of therefrom choosing the fractal dimension extreme value of two horizontal detailed information of reflection and two vertical detailed information of reflection at last are as characterizing cloth textured minutia; Above-mentioned two Sobel operator filtering general picture features and four fractal minutias are formed the composite character vector.The complementarity that has height between each feature of this composite character vector is taken into account the profile information and the detailed information of texture, also takes into account the horizontal information of texture and vertical information, can be comprehensively and portray cloth textured characteristics meticulously.

A kind of be used to characterize cloth textured Sobel operator filtering general picture and fractal details composite character vector extracting method of the present invention, aspect the general picture feature extraction, the fabric original image is handled through Sobel operator horizontal filtering and vertical filtering respectively at first synchronously, obtain the filtering image of two width of cloth correspondences, therefrom extract each gray-scale statistical amount of account form unanimity then respectively and form the proper vector that characterizes cloth textured profile information, one group totally two; Aspect the minutia extraction, at first adopt the one dimension Fast Fourier Transform (FFT) to obtain the horizontal and vertical substantially cycle period size of cloth textured image, then according to each comprises the fractal dimension of subwindow of a laterally basic cycle period and each comprises the fractal dimension of the subwindow of a vertically basic cycle period in the traversal method principle computed image, the last fractal dimension extreme value of therefrom choosing two horizontal detailed information of reflection is horizontal maximum fractal dimension and horizontal minimum fractal dimension, with the fractal dimension extreme values of two vertical detailed information of reflection be vertical maximum fractal dimension and vertical minimum fractal dimension, as characterizing cloth textured minutia.Two Sobel operator filtering general picture features become composite character vector of the present invention with four fractal minutia mutual group.

Wherein said comprise one laterally the subwindow of basic cycle period be to serve as that long and cloth textured image wide is that wide rectangular window, fractal dimension of the subwindow of described each laterally basic cycle period are laterally to add up and calculate on the corresponding one dimension time series basis that forms in the image pixel gray-scale value edge in this subwindow with a laterally basic cycle period.

Described comprise one vertically the subwindow of basic cycle period be that length with a cloth textured image serves as that long and vertically basic cycle period is wide rectangular window, fractal dimension of the subwindow of described each vertically basic cycle period is that the image pixel gray-scale value in this subwindow longitudinally adds up and calculates on the corresponding one dimension time series basis that forms.

The described leaching process that is used to characterize the cloth textured composite character vector of being made up of Sobel operator filtering general picture feature and fractal minutia is as follows:

At first gather the cloth textured image of digitizing, be designated as W, W is a rectangle, its size is long * wide be L ₁* L ₂, promptly horizontal and vertical length is respectively L ₁And L ₂, promptly the row cycle is P and it is along the horizontal basic cycle ₁Individual pixel, the basic cycle longitudinally is that line period is P ₂, the pixel count after line period and row cycle all refer to round, P ₁The basic cycle period of gathering by the arbitrary capable image pixel gray-scale value that calculates W obtains P ₂The basic cycle period of gathering by the arbitrary row image pixel gray-scale value that calculates W obtains.

Original image is implemented Suo Beier operator horizontal filtering and vertical filtering synchronously respectively handle, the image of note behind Suo Beier operator horizontal filtering is W _h, the image after the vertical filtering of Suo Beier operator is W _v

Select a kind of gray-scale statistical amount, directly calculate W then _hThis gray-scale statistical amount, as horizontal edge texture general picture gray-scale statistical measure feature, be designated as S _h

Select and calculating W _hThe time unanimity the gray-scale statistical amount, directly calculate W _vThe gray-scale statistical amount, as vertical edge texture general picture gray-scale statistical measure feature, be designated as S _v

In cloth textured image W, choose a laterally basic cycle period P ₁Wide L for long and cloth textured image ₂For wide rectangular window conduct comprises a horizontal subwindow of cycle period substantially, be designated as W ₁Choose the long L of a cloth textured image ₁Be length, vertically basic cycle period P ₂For wide rectangular window conduct comprises a vertical subwindow of cycle period substantially, be designated as W ₂

For a certain W ₁, calculating the image pixel Gray Projection that it follows direction, the image pixel gray-scale value that is about to each row of this subwindow obtains an one dimension time series along laterally stack, can calculate a fractal dimension from this time series, then with W ₁To travel through whole W, have L with fixed step size slippage flatly ₁-P ₁+ 1 W ₁Thereby, can correspondingly try to achieve L ₁-P ₁+ 1 fractal dimension, note reckling and the maximum wherein is E respectively ₁And E ₂, being horizontal minimum fractal dimension and horizontal maximum fractal dimension, both reflect the lateral extreme detailed information of texture for this;

For a certain W ₂, calculating its image pixel gray-scale value projection along column direction, the image pixel gray-scale value that is about to each row of this subwindow longitudinally superposes, and obtains an one dimension time series, can calculate a fractal dimension from this time series, then with W ₂To travel through whole W, have L with fixed step size slippage vertically ₂-P ₂+ 1 W ₂Thereby, can correspondingly try to achieve L ₂-P ₂+ 1 fractal dimension, note reckling and the maximum wherein is E respectively ₃And E ₄, being vertical minimum fractal dimension and vertical maximum fractal dimension, both reflect the vertically extreme detailed information of texture for this;

Finally obtain characterizing cloth textured composite character vector [S _hS _vE ₁E ₂E ₃E ₄].

Wherein, aforesaid a kind of be used to characterize cloth textured Sobel operator filtering general picture and fractal details composite character vector extracting method, described fabric is a woven fabric.

Aforesaid a kind of cloth textured Sobel operator filtering general picture and fractal details composite character vector extracting method that is used to characterize, the image of described fabric laterally consistent, the image of described fabric vertical consistent with warp thread direction with weft direction.

Aforesaid Sobel operator filtering general picture feature, described gray-scale statistical amount can be the agricultural entropy of celestial being, gray average or gray standard deviation.

Aforesaid a kind of be used to characterize cloth textured Sobel operator filtering general picture and fractal details composite character vector extracting method, described fractal dimension is meant box counting dimension, its concrete computing method are referring to the relevant introduction in the background technology.

Aforesaid a kind of be used to characterize cloth textured Sobel operator filtering general picture and fractal details composite character vector extracting method, used δ size sequence was 2～6 pixels when described box counting dimension was estimated.

Aforesaid a kind of be used to characterize cloth textured Sobel operator filtering general picture and fractal details composite character vector extracting method, described fixed step size refers to 1～3 pixel.

Aforesaid a kind of be used to characterize cloth textured Sobel operator filtering general picture and fractal details composite character vector extracting method, described rectangle subwindow W ₁Each horizontal sliding fixed step size and W ₂Each vertical slippage fixed step size needn't be identical.

Aforesaid a kind of be used to characterize cloth textured Sobel operator filtering general picture and fractal details composite character vector extracting method, wherein above-mentioned basic cycle period P ₁And P ₂Calculating realize by one dimension Fast Fourier Transform (FFT) (FFT).For N point sequence x (n), its FFT transfer pair is defined as

$X\left(k\right)=\underset{n=0}{\overset{N-1}{\mathrm{\Σ}}}x\left(n\right){\mathrm{\ω}}_N^{\mathrm{nk}},k=\mathrm{0,1},L,N-1$

$x\left(n\right)=\frac{1}{N}\underset{k=0}{\overset{N-1}{\mathrm{\Σ}}}X\left(k\right){\mathrm{\ω}}_N^{-\mathrm{nk}},n=\mathrm{0,1},L,N-1$

Wherein,

Be called twiddle factor.

X (k) sequence that sequence of real numbers x (n) obtains after FFT handles is a sequence of complex numbers, first value respective frequencies of this sequence of complex numbers is 0, does not have practical significance, directly with its removal, remaining sequence is a structural symmetry sequence, and the data that only need get its preceding N/2 when carrying out analysis of spectrum get final product.The mould of X (k) is called amplitude, amplitude square be called power, be designated as W.The pairing frequency of peak power is the dominant frequency of sequence x (n), and the inverse of dominant frequency is the basic cycle of this sequence.If the sample frequency of sequence x (n) is f _s(Hz), then the k point is the pairing actual frequency of X (k)

Generally speaking, regulation f _s=1, therefore, Thereby the actual cycle that the k point is corresponding

Aforesaid a kind of be used to characterize cloth textured Sobel operator filtering general picture and fractal details composite character vector extracting method, the first-selected celestial agricultural entropy of described gray-scale statistical amount.Celestial agricultural entropy is an important tolerance of the degree of uncertainty of signal.For image, its quantity of information is big more, and intensity profile is regular more, and corresponding celestial agricultural entropy is just more little, otherwise celestial agricultural entropy is just big more.Celestial agricultural entropy is defined as follows:

$X\left(s\right)=-{\mathrm{\Σ}}_i{s}_i^2{\log }_2\left(s_i^2\right)$

Wherein arrange 0log as usual ₂(0)=0, s _iBe the image pixel gray-scale value.Can directly use the statistic of other kind to replace the agricultural entropy statistic of above-mentioned celestial being.

Beneficial effect

Of the present inventionly a kind ofly be used to characterize that cloth textured Sobel operator filtering general picture and fractal details composite character vector extracting method extracted is used to characterize cloth textured composite character vector:

(1) have the complementarity of height between each feature, take into account the profile information and the detailed information of texture, also take into account the horizontal information of texture and vertical information, can be comprehensively and portray cloth textured characteristics meticulously;

(2) the complementation between profile information and detailed information, fractal characteristic belongs to two kinds of different texture characterizing methods with Sobel operator filtering feature itself, emphasizes particularly on different fields, thereby also has the characteristic effect complementary effect that causes because of method divergence between them;

(3) calculating of Sobel operator filtering general picture feature is not owing to need filtering image is implemented binary conversion treatment, therefore kept how useful transitional information in the filtering image, and be not only simple two value informations, and therefore need not to spend preferred binary-state threshold time, make computation process become simple and efficient;

(4) thus in fractal minutia leaching process, made full use of the cloth textured characteristics that its main information of warp-wise and broadwise orientation concentrates on warp-wise and broadwise that have, on the basis of the vertical or horizontal one dimension projection sequence of image subwindow but not calculate on the two dimensional image basis, both keep most Useful Informations, reduced calculated amount again significantly;

(5) calculating of fractal minutia has made full use of cloth textured distinctive cycline rule characteristics, thereby the feature that calculates is stable more and press close to true.

Correlative study does not in the past then possess above-mentioned five advantages.

Description of drawings

Fig. 1 is that cloth textured composite character vector of the present invention extracts synoptic diagram

Fig. 2 is the textile image of the width of cloth 64*64 pixel size of embodiment 1

Fig. 3 is the image of embodiment 1 former figure behind Sobel operator horizontal filtering

Fig. 4 is the image of embodiment 1 former figure after the vertical filtering of Sobel operator

Fig. 5 is the textile image of the width of cloth 64*64 pixel size of embodiment 2

Fig. 6 is the images of embodiment 2 former figure behind Sobel operator horizontal filtering

Fig. 7 is the images of embodiment 2 former figure after the vertical filtering of Sobel operator

Fig. 8 is the textile image of the width of cloth 64*64 pixel size of embodiment 3

Fig. 9 is the images of embodiment 3 former figure behind Sobel operator horizontal filtering

Figure 10 is the images of embodiment 3 former figure after the vertical filtering of Sobel operator

Embodiment

Below in conjunction with embodiment, further set forth the present invention.Should be understood that these embodiment only to be used to the present invention is described and be not used in and limit the scope of the invention.Should be understood that in addition those skilled in the art can make various changes or modifications the present invention after the content of having read the present invention's instruction, these equivalent form of values fall within the application's appended claims institute restricted portion equally.

A kind of be used to characterize cloth textured Sobel operator filtering general picture and fractal details composite character vector extracting method of the present invention, aspect the general picture feature extraction, the fabric original image is handled through Sobel operator horizontal filtering and vertical filtering respectively at first synchronously, obtain the filtering image of two width of cloth correspondences, therefrom extract each gray-scale statistical amount of account form unanimity then respectively and form the proper vector that characterizes cloth textured profile information, one group totally two; Aspect the minutia extraction, at first adopt the one dimension Fast Fourier Transform (FFT) to obtain the horizontal and vertical substantially cycle period size of cloth textured image, then according to each comprises the fractal dimension of subwindow of a laterally basic cycle period and each comprises the fractal dimension of the subwindow of a vertically basic cycle period in the traversal method principle computed image, the fractal dimension extreme values (being vertical maximum fractal dimension and vertical minimum fractal dimension) of therefrom choosing the fractal dimension extreme value (being horizontal maximum fractal dimension and horizontal minimum fractal dimension) of two horizontal detailed information of reflection and two vertical detailed information of reflection at last are as the cloth textured minutia of sign.Two Sobel operator filtering general picture features become composite character vector of the present invention with four fractal minutia mutual group.

Wherein said comprise one laterally the subwindow of basic cycle period be to serve as that long and cloth textured image wide is that wide rectangular window, fractal dimension of the subwindow of described each laterally basic cycle period are laterally to add up and calculate on the corresponding one dimension time series basis that forms in the image pixel gray-scale value edge in this subwindow with a laterally basic cycle period.

Described comprise one vertically the subwindow of basic cycle period be that length with a cloth textured image serves as that long and vertically basic cycle period is wide rectangular window, fractal dimension of the subwindow of described each vertically basic cycle period is that the image pixel gray-scale value in this subwindow longitudinally adds up and calculates on the corresponding one dimension time series basis that forms.

The described leaching process that is used to characterize the cloth textured composite character vector of being made up of Sobel operator filtering general picture feature and fractal minutia is as follows:

At first gather the cloth textured image of digitizing, be designated as W, W is a rectangle, its size is long * wide be L ₁* L ₂, promptly horizontal and vertical length is respectively L ₁And L ₂, promptly the row cycle is P and it is along the horizontal basic cycle ₁Individual pixel, the basic cycle longitudinally is that line period is P ₂, the pixel count after line period and row cycle all refer to round, P ₁The basic cycle period of gathering by the arbitrary capable image pixel gray-scale value that calculates W obtains P ₂The basic cycle period of gathering by the arbitrary row image pixel gray-scale value that calculates W obtains.

Original image is implemented Suo Beier operator horizontal filtering and vertical filtering synchronously respectively handle, the image of note behind Suo Beier operator horizontal filtering is W _h, the image after the vertical filtering of Suo Beier operator is W _v

Select a kind of gray-scale statistical amount, directly calculate W then _hThis gray-scale statistical amount, as horizontal edge texture general picture gray-scale statistical measure feature, be designated as S _h

Select and calculating W _hThe time unanimity the gray-scale statistical amount, directly calculate W _vThe gray-scale statistical amount, as vertical edge texture general picture gray-scale statistical measure feature, be designated as S _v

In cloth textured image W, choose a laterally basic cycle period P ₁Wide L for long and cloth textured image ₂For wide rectangular window conduct comprises a horizontal subwindow of cycle period substantially, be designated as W ₁Choose the long L of a cloth textured image ₁Be length, vertically basic cycle period P ₂For wide rectangular window conduct comprises a vertical subwindow of cycle period substantially, be designated as W ₂

For a certain W ₁, calculating the image pixel Gray Projection that it follows direction, the image pixel gray-scale value that is about to each row of this subwindow obtains an one dimension time series along laterally stack, can calculate a fractal dimension from this time series, then with W ₁To travel through whole W, have L with fixed step size slippage flatly ₁-P ₁+ 1 W ₁Thereby, can correspondingly try to achieve L ₁-P ₁+ 1 fractal dimension, note reckling and the maximum wherein is E respectively ₁And E ₂, being horizontal minimum fractal dimension and horizontal maximum fractal dimension, both reflect the lateral extreme detailed information of texture for this;

For a certain W ₂, calculating its image pixel gray-scale value projection along column direction, the image pixel gray-scale value that is about to each row of this subwindow longitudinally superposes, and obtains an one dimension time series, can calculate a fractal dimension from this time series, then with W ₂To travel through whole W, have L with fixed step size slippage vertically ₂-P ₂+ 1 W ₂Thereby, can correspondingly try to achieve L ₂-P ₂+ 1 fractal dimension, note reckling and the maximum wherein is E respectively ₃And E ₄, being vertical minimum fractal dimension and vertical maximum fractal dimension, both reflect the vertically extreme detailed information of texture for this;

Finally obtain characterizing cloth textured composite character vector [S _hS _vE ₁E ₂E ₃E ₄].

Wherein aforesaid a kind of be used to characterize cloth textured Sobel operator filtering general picture and fractal details composite character vector extracting method, described fabric is a woven fabric.

Aforesaid a kind of cloth textured Sobel operator filtering general picture and fractal details composite character vector extracting method that is used to characterize, the image of described fabric laterally consistent, the image of described fabric vertical consistent with warp thread direction with weft direction.

Aforesaid Sobel operator filtering general picture feature, described gray-scale statistical amount can be the agricultural entropy of celestial being, gray average or gray standard deviation.

Aforesaid a kind of be used to characterize cloth textured Sobel operator filtering general picture and fractal details composite character vector extracting method, described fractal dimension is meant box counting dimension, its concrete computing method are referring to the relevant introduction in the background technology.

Aforesaid a kind of be used to characterize cloth textured Sobel operator filtering general picture and fractal details composite character vector extracting method, used δ size sequence was 2～6 pixels when described box counting dimension was estimated.

Aforesaid a kind of be used to characterize cloth textured Sobel operator filtering general picture and fractal details composite character vector extracting method, described fixed step size refers to 1～3 pixel.

Aforesaid a kind of be used to characterize cloth textured Sobel operator filtering general picture and fractal details composite character vector extracting method, described rectangle subwindow W ₁Each horizontal sliding step-length and W ₂Each vertical slippage step-length needn't be identical.

Aforesaid a kind of be used to characterize cloth textured Sobel operator filtering general picture and fractal details composite character vector extracting method, wherein above-mentioned basic cycle period P ₁And P ₂Calculating realize by one dimension Fast Fourier Transform (FFT) (FFT).

Aforesaid a kind of be used to characterize cloth textured Sobel operator filtering general picture and fractal details composite character vector extracting method, the first-selected celestial agricultural entropy of described gray-scale statistical amount.

Can directly use the statistic of other kind to replace the agricultural entropy statistic of above-mentioned celestial being.

Be further described below in conjunction with accompanying drawing:

(1) gather the cloth textured image of digitizing, be designated as W, shown in the rectangle ABCD among Fig. 1, it is of a size of L ₁* L ₂Pixel, promptly laterally (AD) and vertical (AB) length are respectively L ₁Pixel and L ₂Pixel;

(2) original image is implemented Suo Beier operator horizontal filtering and vertical filtering synchronously respectively and handle, the image of note behind Suo Beier operator horizontal filtering is W _h, the image after the vertical filtering of Suo Beier operator is W _v

(3) select a kind of gray-scale statistical amount from the agricultural entropy of celestial being, gray average, gray variance, first-selected celestial agricultural entropy directly calculates W then _hThis gray-scale statistical amount, as horizontal edge texture general picture gray-scale statistical measure feature, be designated as S _h

(4) select and calculating W _hThe time unanimity the gray-scale statistical amount, directly calculate W _vThe gray-scale statistical amount, as vertical edge texture general picture gray-scale statistical measure feature, be designated as S _v

(5) extract the arbitrary capable pixel grey scale value set of cloth textured image to be analyzed, Fast Fourier Transform (FFT) is tried to achieve it and promptly is listed as basic cycle P along the horizontal basic cycle by one dimension ₁

(6) extract arbitrary row pixel grey scale value set of cloth textured image to be analyzed, its basic cycle longitudinally basic cycle P is at once tried to achieve in Fast Fourier Transform (FFT) by one dimension ₂

(7) in W, appoint and get one as rectangle A ₁B ₁C ₁D ₁Shown subwindow is noted by abridging to being designated as W ₁, this subwindow lateral length is P ₁And longitudinal length is L ₂, for this W ₁, calculating the image pixel gray-scale value projection that it follows direction, the image pixel gray-scale value that is about to each row of this subwindow is along laterally stack, obtain an one dimension time series, in δ size sequence is under the prerequisite of 2～6 pixels, can calculate a box counting dimension feature from this time series, then with W ₁With the fixed step size slippage flatly of each 1～3 pixel to travel through whole W, total L ₁-P ₁+ 1 W ₁Thereby, can correspondingly try to achieve L ₁-P ₁+ 1 box counting dimension feature, note reckling and the maximum wherein is E respectively ₁And E ₂

(8) in W, appoint and get one as rectangle A ₂B ₂C ₂D ₂Shown subwindow is noted by abridging to being designated as W ₂, this subwindow lateral length is L ₁And longitudinal length is P ₂, for this W ₂, calculating its image pixel gray-scale value projection along column direction, the image pixel gray-scale value that is about to each row of this subwindow longitudinally superposes, obtain an one dimension time series, in δ size sequence is under the prerequisite of 2～6 pixels, can calculate a box counting dimension feature from this time series, then with W ₂With the fixed step size slippage vertically of each 1～3 pixel to travel through whole W, total L ₂-P ₂+ 1 W ₂Thereby, can correspondingly try to achieve L ₂-P ₂+ 1 box counting dimension feature, note reckling and the maximum wherein is E respectively ₃And E ₄

(9) obtain characterizing cloth textured proper vector [S _hS _vE ₁E ₂E ₃E ₄].

Embodiment 1

(1) obtain textile image W, this image size is 64 * 64 pixels, as shown in Figure 2.

(2) W is implemented Sobel operator horizontal filtering, obtain image as shown in Figure 3, be designated as W _h

(3) W is implemented the vertical filtering of Sobel operator, obtain image as shown in Figure 4, be designated as W _v

(4) select celestial agricultural entropy as the gray-scale statistical amount, celestial agricultural entropy computing formula is as follows:

$X\left(s\right)=-{\mathrm{\Σ}}_i{s}_i^2{\log }_2\left(s_i^2\right)$

(5) calculate W _hCelestial agricultural entropy be S _h, as horizontal edge texture general picture gray-scale statistical measure feature, the result is-5.23 * 10 ⁷

(6) calculate W _vCelestial agricultural entropy be S _v, as vertical edge texture general picture gray-scale statistical measure feature, the result is-9.51 * 10 ⁷

(7) adopt one dimension FFT that the arbitrary capable gradation data of former figure is carried out computation of Period, obtain being listed as basic cycle P ₁=6 pixels.

(8) adopt one dimension FFT that arbitrary row gradation data of former figure is carried out computation of Period, obtain row basic cycle P ₂=4 pixels.

(9) in W, get as rectangle A among Fig. 1 ₁B ₁C ₁D ₁Shown subwindow W ₁This subwindow lateral length is 6 pixels and longitudinal length is 64 pixels, each row image pixel gray-scale value of this subwindow is along the transverse projection one dimension time series that can to obtain a length be 64 pixels, then according to traversal method principle, elect 1 pixel as and δ size sequence is under the situation of 2～6 pixels at subwindow slippage fixed step size, can try to achieve a series of corresponding box counting dimensions on a series of one dimension time series basis, reckling wherein and the maximum are respectively 1.42 and 1.48.

(10) in W, get as rectangle A among Fig. 1 ₂B ₂C ₂D ₂Shown subwindow W ₂This subwindow lateral length is 64 pixels and longitudinal length is 4 pixels, the one dimension time series that it is 64 pixels that each the row image pixel gray-scale value projection longitudinally of this subwindow can obtain a length, then according to traversal method principle, elect 1 pixel as and δ size sequence is under the situation of 2～6 pixels at subwindow slippage fixed step size, can try to achieve a series of corresponding box counting dimensions on a series of one dimension time series basis, reckling wherein and the maximum are respectively 1.44 and 1.47.

(11) finally obtain characterizing cloth textured composite character vector [5.23 * 10 ⁷-9.51 * 10 ⁷1.421.481.441.47].

Embodiment 2

(1) obtain textile image W, this image size is 64 * 64 pixels, as shown in Figure 5.

(2) W is implemented Sobel operator horizontal filtering, obtain image as shown in Figure 6, be designated as W _h

(3) W is implemented the vertical filtering of Sobel operator, obtain image as shown in Figure 7, be designated as W _v

(4) select gray average as the gray-scale statistical amount, the gray average computing formula is as follows:

$X\left(s\right)=\frac{1}{n}\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{s}_i$

(5) calculate W _hGray average be S _h, as horizontal edge texture general picture gray-scale statistical measure feature, the result is 86.84.

(6) calculate W _vGray average be S _v, as vertical edge texture general picture gray-scale statistical measure feature, the result is 88.69.

(7) adopt one dimension FFT that the arbitrary capable gradation data of former figure is carried out computation of Period, obtain being listed as basic cycle P ₁=20 pixels.

(8) adopt one dimension FFT that arbitrary row gradation data of former figure is carried out computation of Period, obtain row basic cycle P ₂=11 pixels.

(9) in W, get as rectangle A among Fig. 1 ₁B ₁C ₁D ₁Shown subwindow W ₁This subwindow lateral length is 20 pixels and longitudinal length is 64 pixels, each row image pixel gray-scale value of this subwindow is along the transverse projection one dimension time series that can to obtain a length be 64 pixels, then according to traversal method principle, elect 2 pixels as and δ size sequence is under the situation of 2～6 pixels at subwindow slippage fixed step size, can try to achieve a series of corresponding box counting dimensions on a series of one dimension time series basis, reckling wherein and the maximum are respectively 1.33 and 1.45.

(10) in W, get as rectangle A among Fig. 1 ₂B ₂C ₂D ₂Shown subwindow W ₂This subwindow lateral length is 64 pixels and longitudinal length is 11 pixels, the one dimension time series that it is 64 pixels that each the row image pixel gray-scale value projection longitudinally of this subwindow can obtain a length, then according to traversal method principle, elect 1 pixel as and δ size sequence is under the situation of 2～6 pixels at subwindow slippage fixed step size, can try to achieve a series of corresponding box counting dimensions on a series of one dimension time series basis, reckling wherein and the maximum are respectively 1.30 and 1.47.

(11) finally obtain characterizing cloth textured composite character vector [86.8488.691.331.451.301.47].

Embodiment 3

(1) obtain textile image W, this image size is 64 * 64 pixels, as shown in Figure 8.

(2) W is implemented Sobel operator horizontal filtering, obtain image as shown in Figure 9, be designated as W _h

(3) W is implemented the vertical filtering of Sobel operator, obtain image as shown in figure 10, be designated as W _v

(4) select gray standard deviation as the gray-scale statistical amount, the gray standard deviation computing formula is as follows:

Standard deviation $X\left(s\right)=\sqrt{\frac{1}{n-1}\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{(s_i-\stackrel{\‾}{s})}^2},$ Wherein, $\stackrel{\‾}{s}=\frac{1}{n}\underset{i=1}{\overset{n}{\mathrm{\Σ}}}{s}_i$

(5) calculate W _hGray standard deviation be S _h, as horizontal edge texture general picture gray-scale statistical measure feature, the result is 110.8.

(6) calculate W _vGray standard deviation be S _v, as vertical edge texture general picture gray-scale statistical measure feature, the result is 115.9.

(7) adopt one dimension FFT that the arbitrary capable gradation data of former figure is carried out computation of Period, obtain being listed as basic cycle P ₁=8 pixels.

(8) adopt one dimension FFT that arbitrary row gradation data of former figure is carried out computation of Period, obtain row basic cycle P ₂=15 pixels.

(9) in W, get as rectangle A among Fig. 1 ₁B ₁C ₁D ₁Shown subwindow W ₁This subwindow lateral length is 8 pixels and longitudinal length is 64 pixels, each row image pixel gray-scale value of this subwindow is along the transverse projection one dimension time series that can to obtain a length be 64 pixels, then according to traversal method principle, elect 2 pixels as and δ size sequence is under the situation of 2～6 pixels at subwindow slippage fixed step size, can try to achieve a series of corresponding box counting dimensions on a series of one dimension time series basis, reckling wherein and the maximum are respectively 1.21 and 1.29.

(10) in W, get as rectangle A among Fig. 1 ₂B ₂C ₂D ₂Shown subwindow W ₂This subwindow lateral length is 64 pixels and longitudinal length is 15 pixels, the one dimension time series that it is 64 pixels that each the row image pixel gray-scale value projection longitudinally of this subwindow can obtain a length, then according to traversal method principle, elect 3 pixels as and δ size sequence is under the situation of 2～6 pixels at subwindow slippage fixed step size, can try to achieve a series of corresponding box counting dimensions on a series of one dimension time series basis, reckling wherein and the maximum are respectively 1.25 and 1.33.

(11) finally obtain characterizing cloth textured composite character vector [110.8115.91.211.291.251.33].

Claims (10)

1. one kind is used to characterize cloth textured Sobel operator filtering general picture and fractal details composite character vector extracting method, and it is characterized in that: described composite character vector is made of jointly two Sobel operator filtering general picture features and four fractal minutias;

The general picture feature extraction: the fabric original image is handled through Sobel operator horizontal filtering and vertical filtering respectively at first synchronously, obtain the filtering image of two width of cloth correspondences, therefrom extract each gray-scale statistical amount of account form unanimity then respectively and form the proper vector that characterizes cloth textured profile information;

Minutia is extracted: at first adopt the one dimension Fast Fourier Transform (FFT) to obtain the horizontal and vertical substantially cycle period size of cloth textured image, then according to each comprises the fractal dimension of subwindow of a laterally basic cycle period and each comprises the fractal dimension of the subwindow of a vertically basic cycle period in the traversal method principle computed image, the last fractal dimension extreme value of therefrom choosing two horizontal detailed information of reflection is horizontal maximum fractal dimension and horizontal minimum fractal dimension, with the fractal dimension extreme values of two vertical detailed information of reflection be vertical maximum fractal dimension and vertical minimum fractal dimension, as characterizing cloth textured minutia;

Wherein

Described comprise one laterally the subwindow of basic cycle period be to serve as that long and cloth textured image wide is that wide rectangular window, fractal dimension of the subwindow of described each laterally basic cycle period are laterally to add up and calculate on the corresponding one dimension time series basis that forms in the image pixel gray-scale value edge in this subwindow with a laterally basic cycle period;

Described comprise one vertically the subwindow of basic cycle period be that length with a cloth textured image serves as that long and vertically basic cycle period is wide rectangular window, fractal dimension of the subwindow of described each vertically basic cycle period is that the image pixel gray-scale value in this subwindow longitudinally adds up and calculates on the corresponding one dimension time series basis that forms;

The described leaching process that is used to characterize the cloth textured composite character vector of being made up of Sobel operator filtering general picture feature and fractal minutia is as follows:

At first gather the cloth textured image of digitizing, be designated as W, W is a rectangle, its size is long * wide be L ₁* L ₂, promptly horizontal and vertical length is respectively L ₁And L ₂, promptly the row cycle is P and it is along the horizontal basic cycle ₁Individual pixel, the basic cycle longitudinally is that line period is P ₂Individual pixel, the pixel count after line period and row cycle all refer to round, P ₁The basic cycle period of gathering by the arbitrary capable image pixel gray-scale value that calculates W obtains P ₂The basic cycle period of gathering by the arbitrary row image pixel gray-scale value that calculates W obtains;

Original image is implemented Suo Beier operator horizontal filtering and vertical filtering synchronously respectively handle, the image of note behind Suo Beier operator horizontal filtering is W _h, the image after the vertical filtering of Suo Beier operator is W _v

Select a kind of gray-scale statistical amount, directly calculate W then _hThis gray-scale statistical amount, as horizontal edge texture general picture gray-scale statistical measure feature, be designated as S _h

Select and calculating W _hThe time unanimity the gray-scale statistical amount, directly calculate W _vThe gray-scale statistical amount, as vertical edge texture general picture gray-scale statistical measure feature, be designated as S _v

In cloth textured image W, choose a laterally basic cycle period P ₁Wide L for long and cloth textured image ₂For wide rectangular window conduct comprises a horizontal subwindow of cycle period substantially, be designated as W ₁Choose the long L of a cloth textured image ₁Be length, vertically basic cycle period P ₂For wide rectangular window conduct comprises a vertical subwindow of cycle period substantially, be designated as W ₂

For a certain W ₁, calculating the image pixel Gray Projection that it follows direction, the image pixel gray-scale value that is about to each row of this subwindow obtains an one dimension time series along laterally stack, can calculate a fractal dimension from this time series, then with W ₁To travel through whole W, have L with fixed step size slippage flatly ₁-P ₁+ 1 W ₁Thereby, can correspondingly try to achieve L ₁-P ₁+ 1 fractal dimension, note reckling and the maximum wherein is E respectively ₁And E ₂, being horizontal minimum fractal dimension and horizontal maximum fractal dimension, both reflect the lateral extreme detailed information of texture for this;

For a certain W ₂, calculating its image pixel gray-scale value projection along column direction, the image pixel gray-scale value that is about to each row of this subwindow longitudinally superposes, and obtains an one dimension time series, can calculate a fractal dimension from this time series, then with W ₂To travel through whole W, have L with fixed step size slippage vertically ₂-P ₂+ 1 W ₂Thereby, can correspondingly try to achieve L ₂-P ₂+ 1 fractal dimension, note reckling and the maximum wherein is E respectively ₃And E ₄, being vertical minimum fractal dimension and vertical maximum fractal dimension, both reflect the vertically extreme detailed information of texture for this;

Finally obtain characterizing cloth textured Sobel operator filtering general picture and fractal details composite character vector [S _hS _vE ₁E ₂E ₃E ₄].

2. a kind of be used to characterize cloth textured Sobel operator filtering general picture and fractal details composite character vector extracting method as claimed in claim 1 is characterized in that described fabric is a woven fabric.

3. a kind of be used to characterize cloth textured Sobel operator filtering general picture and fractal details composite character vector extracting method as claimed in claim 1, the image of described fabric laterally consistent with weft direction, the image of described fabric vertical consistent with warp thread direction.

4. a kind of be used to characterize cloth textured Sobel operator filtering general picture and fractal details composite character vector extracting method as claimed in claim 1 is characterized in that described gray-scale statistical amount is celestial agricultural entropy, gray average or gray standard deviation.

5. as claim 1 or 4 described a kind of be used to characterize cloth textured Sobel operator filtering general picture and fractal details composite character vector extracting method, it is characterized in that the first-selected celestial agricultural entropy of described gray-scale statistical amount.

6. a kind of be used to characterize cloth textured Sobel operator filtering general picture and fractal details composite character vector extracting method as claimed in claim 1 is characterized in that described fractal dimension is meant box counting dimension.

7. a kind of be used to characterize cloth textured Sobel operator filtering general picture and fractal details composite character vector extracting method as claimed in claim 6 is characterized in that used δ size sequence was 2～6 pixels when described box counting dimension was estimated.

8. a kind of be used to characterize cloth textured Sobel operator filtering general picture and fractal details composite character vector extracting method as claimed in claim 1 is characterized in that described fixed step size refers to 1～3 pixel.

9. a kind of be used to characterize cloth textured Sobel operator filtering general picture and fractal details composite character vector extracting method as claimed in claim 1 is characterized in that described rectangle subwindow W ₁Each horizontal sliding fixed step size and W ₂Each vertical slippage fixed step size needn't be identical.

10. a kind of be used to characterize cloth textured Sobel operator filtering general picture and fractal details composite character vector extracting method as claimed in claim 1 is characterized in that described basic cycle period P ₁And P ₂Calculating realize by the one dimension Fast Fourier Transform (FFT).

Images