CN105678341A - Wool cashmere recognition algorithm based on Gabor wavelet analysis - Google Patents

Abstract

The invention discloses a wool cashmere recognition algorithm based on Gabor wavelet analysis, and the algorithm comprises an online recognition flow and a model learning flow. The online recognition flow comprises the following steps: (1), taking an image of wool cashmere fibers (2), carrying out the smooth filtering of the image through employing a Gaussian filter, and achieving the image enhancement through the gray scale adjustment of the image; (3), extracting an image target through employing the edge detection and contour extraction based on canny; (4), extracting Gabor characteristics; (5), calculating a result. The model learning model comprises the following steps: (1), accumulating a large amount of wool cashmere data in a database; (2), determining the class of a target fiber and the position of the target fiber through manual marking; (3), carrying out the preprocessing and feature extraction of the fiber image in the database, wherein the step (3) is consistent with the steps (2) and (4) in the online recognition flow; (4), employing a two-class SVM classifier in a learning process. The method can achieve a high recognition rate, is quick in recognition speed, is high in accuracy of the recognition result, and is high in applicability.

Description

A kind of woollen and cashmere recognizer analyzed based on Gabor wavelet

Technical field

The invention belongs to woollen and cashmere identification technical field, particularly relate to a kind of woollen and cashmere recognizer analyzed based on Gabor wavelet.

Background technology

Cashmere fiber is elongated, uniform, soft, has soft sliding warm feature with its textile made, and is the first-selection that faces of high-grade dress ornament. Owing to its yield is rare, on the high side, the Cashmere and Woolens of the conventional different proportion of manufacturing enterprise carries out blending. Pilus Caprae seu Ovis and cashmere broadly fall into natural protein fibre, and its structure and form all closely, carry out the normal difficulty that judges between right and wrong of kinds of fibers accurately.

Fibre identification method conventional at present is microscopic method. The composition of Cashmere and Woolens, by observing the features such as scale shape and the grain details of woollen and cashmere under the microscope, is carried out qualitative classification according to its personal experience by testing staff, and this mode not only takes time and effort, and subjectivity is big, and the concordance of measurement is also poor.

Reference standard of the present invention: 1,2,3, the full automatic Cashmere and Woolens recognition methods of a kind of intelligence is proposed, first with microscope and the CCD image acquisition that Cashmere and Woolens is digitized, Cashmere and Woolens image is carried out the wavelet convolution under different scale and extracts feature by recycling, and utilizes SVM to build sorter model, it is achieved the intelligent classification identification to Cashmere and Woolens.

Gabor wavelet is closely similar with the visual stimulus response of simple cell in human visual system. It has good characteristic in the local space extracting target and frequency-domain information. Gabor wavelet is for the edge sensitive of image, using the teaching of the invention it is possible to provide good set direction and scale selection characteristic, and insensitive for illumination variation, using the teaching of the invention it is possible to provide the adaptability that illumination variation is good. Two-Dimensional Gabor Wavelets conversion is the important tool carrying out signal analysis and processing at time-frequency domain, and its conversion coefficient has good visual characteristic and Biological background, is therefore widely used in the field such as image procossing, pattern recognition. Compared with traditional Fourier transform, Gabor wavelet conversion has good Time-Frequency Localization characteristic.

Summary of the invention

The present invention provides a kind of woollen and cashmere recognizer analyzed based on Gabor wavelet, can reach discrimination height, and recognition speed is fast, and recognition result accuracy rate is high, the beneficial effect that the suitability is strong.

Technical problem solved by the invention realizes by the following technical solutions: the present invention provides a kind of woollen and cashmere recognizer analyzed based on Gabor wavelet, including ONLINE RECOGNITION flow process and model learning flow process:

Described ONLINE RECOGNITION flow process, carries out qualitative analysis to the fibre image of Real-time Collection, comprises the following steps:

(1) acquisition of image, adopts 3,000,000 pixel technical grade ccd to coordinate Olympus CX41 biological microscope, Cashmere and Woolens fiber is carried out capture;

(2) pretreatment: a adopts Gaussian filter that image is carried out smothing filtering, to remove the noise in image, Gaussian filter is a kind of low pass filter, and its process can Formal Representation be input picture I (x, y) with gaussian kernel function G (x, convolution y):

S (x, y)=I (x, y) × G (x, y; σ) wherein

Image gray levels adjustment is realized image enhaucament by b, if data x_ijIt is the i row j column element in image X, max_x, min_xIt is maximum, the minima in X respectively; $x_{ij}=\frac{x_{ij}-{\min }_X}{{\max }_X-{\min }_X}\×255;$

(3) image object extracts: adopting the extraction of the rim detection based on canny and profile, canny rim detection is a multistage edge detection algorithm; Its basic step mainly has: a obtains the gradient of x, y, and the non-maximum of b suppresses, c Edge track, directly adopts the canny operator inside opencv here;

(4) Gabor wavelet feature extraction: point 5 40,8 directions of yardstick Feature Descriptors; PCA dimensionality reduction is adopted to tie up to 100;

Gabor function can extract relevant feature on frequency domain different scale, different directions; Two-dimensional Gabor function can be expressed as:

$g_{uv}(x,y)=\frac{k^2}{{\mathrm{\σ}}^2}\exp (-\frac{k^2(x^2+y^2)}{2{\mathrm{\σ}}^2})\[\exp \left(ik\left(\begin{array}{c}x\\ y\end{array}\right)\right)-\exp (-\frac{{\mathrm{\σ}}^2}{2})\]$

Wherein: $k_v=2^{-\frac{v+2}{2}}\mathrm{\π},$

Choose the Gabor base in one group of different scale and direction and input fibre image carried out convolution, specifically choose 4 yardsticks (v=0,1 ..., 3), 8 directions (i.e. K=8, u=0,1 ..., 7), totally 32 Gabor kernel functions;

(5) characteristic vector is inputted classifier calculated result; It is scaled 48*48 size by unified for each fibre image of input, then extracts the Gabor characteristic collection of illustrative plates under 32 yardsticks, extract 48*48*32=73728 dimensional vector altogether; We take PCA method that original high dimensional data is down to 100 dimensions further, as the input feature value of SVM;

Described model learning flow process, is to obtain a grader, takes a kind of sorter model based on SVM, comprise the following steps:

(1) premise of model learning is the data base of the substantial amounts of woollen and cashmere of accumulation;

(2) on this basis, adopt the mode of artificial mark, make kind and the location of machine hard objectives fiber, be a kind of supervised learning mode;

(3) fibre image in data base being carried out pretreatment, feature extraction, this step is consistent with (2) (4) step of ONLINE RECOGNITION flow process;

(4) learning process takes the SVM classifier of two classification, and utilizes the libSVM increased income to be trained, and chooses RBF Radial basis kernel function, and iterations is set to 100000 times, iteration ends deviation 0.001.

The invention have the benefit that

The present invention is high to the discrimination of Cashmere and Woolens, and recognition speed is fast, and recognition result accuracy rate is high and the suitability is strong.

Accompanying drawing explanation

Fig. 1 is the schematic flow sheet of the present invention.

Detailed description of the invention

Embodiment:

Present invention resides in line identification process and model learning flow process:

Described ONLINE RECOGNITION flow process, carries out qualitative analysis to the fibre image of Real-time Collection, comprises the following steps:

(1) acquisition of image, adopts 3,000,000 pixel technical grade ccd to coordinate Olympus CX41 biological microscope, Cashmere and Woolens fiber is carried out capture;

(2) pretreatment: a adopts Gaussian filter that image is carried out smothing filtering, to remove the noise in image, Gaussian filter is a kind of low pass filter, and its process can Formal Representation be input picture I (x, y) with gaussian kernel function G (x, convolution y):

S (x, y)=I (x, y) × G (x, y; σ) wherein

Image gray levels adjustment is realized image enhaucament by b, if data x_ijIt is the i row j column element in image X, max_x, min_xIt is maximum, the minima in X respectively; $x_{ij}=\frac{x_{ij}-{\min }_X}{{\max }_X-{\min }_X}\×255;$

(3) image object extracts: adopting the extraction of the rim detection based on canny and profile, canny rim detection is a multistage edge detection algorithm; Its basic step mainly has: a obtains the gradient of x, y, and the non-maximum of b suppresses, c Edge track, directly adopts the canny operator inside opencv here;

(4) Gabor wavelet feature extraction: point 5 40,8 directions of yardstick Feature Descriptors; PCA dimensionality reduction is adopted to tie up to 100;

Gabor function can extract relevant feature on frequency domain different scale, different directions; Two-dimensional Gabor function can be expressed as:

$g_{uv}(x,y)=\frac{k^2}{{\mathrm{\σ}}^2}\exp (-\frac{k^2(x^2+y^2)}{2{\mathrm{\σ}}^2})\[\exp \left(ik\left(\begin{array}{c}x\\ y\end{array}\right)\right)-\exp (-\frac{{\mathrm{\σ}}^2}{2})\]$

Wherein: $k_v=2^{-\frac{v+2}{2}}\mathrm{\π},$

Choose the Gabor base in one group of different scale and direction and input fibre image carried out convolution, specifically choose 4 yardsticks (v=0,1 ..., 3), 8 directions (i.e. K=8, u=0,1 ..., 7), totally 32 Gabor kernel functions;

(5) characteristic vector is inputted classifier calculated result; It is scaled 48*48 size by unified for each fibre image of input, then extracts the Gabor characteristic collection of illustrative plates under 32 yardsticks, extract 48*48*32=73728 dimensional vector altogether; We take PCA method that original high dimensional data is down to 100 dimensions further, as the input feature value of SVM;

Described model learning flow process, is to obtain a grader, takes a kind of sorter model based on SVM, comprise the following steps:

(1) premise of model learning is the data base of the substantial amounts of woollen and cashmere of accumulation;

(2) on this basis, adopt the mode of artificial mark, make kind and the location of machine hard objectives fiber, be a kind of supervised learning mode;

(3) fibre image in data base being carried out pretreatment, feature extraction, this step is consistent with (2) (4) step of ONLINE RECOGNITION flow process;

(4) learning process takes the SVM classifier of two classification, and utilizes the libSVM increased income to be trained, and chooses RBF Radial basis kernel function, and iterations is set to 100000 times, iteration ends deviation 0.001.

Above by embodiment being described in detail the present invention, but described content is only presently preferred embodiments of the present invention, it is impossible to be considered the practical range for limiting the present invention. All utilize technical solutions according to the invention; or those skilled in the art is under the inspiration of technical solution of the present invention; design similar technical scheme and reach above-mentioned technique effect; or impartial change and improvement etc. that application range is made, the patent that all should still belong to the present invention contains within protection domain.

Claims (1)

1. the woollen and cashmere recognizer analyzed based on Gabor wavelet, it is characterised in that: include ONLINE RECOGNITION flow process and model learning flow process:

Described ONLINE RECOGNITION flow process, carries out qualitative analysis to the fibre image of Real-time Collection, comprises the following steps:

(1) acquisition of image, adopts 3,000,000 pixel technical grade ccd to coordinate Olympus CX41 biological microscope, Cashmere and Woolens fiber is carried out capture;

(2) pretreatment: a adopts Gaussian filter that image is carried out smothing filtering, to remove the noise in image, Gaussian filter is a kind of low pass filter, and its process can Formal Representation be input picture I (x, y) with gaussian kernel function G (x, convolution y):

S (x, y)=I (x, y) × G (x, y;σ) wherein $G(x,y)=\frac{1}{2{\mathrm{\π\σ}}^2}\exp (-\frac{x^2+y^2}{2{\mathrm{\σ}}^2})$

Image gray levels adjustment is realized image enhaucament by b, if data x_ijIt is the i row j column element in image X, max_x, min_xIt is maximum, the minima in X respectively; $x_{ij}=\frac{x_{ij}-{\min }_X}{{\max }_X-{\min }_X}\×255;$

(3) image object extracts: adopting the extraction of the rim detection based on canny and profile, canny rim detection is a multistage edge detection algorithm; Its basic step mainly has: a obtains the gradient of x, y, and the non-maximum of b suppresses, c Edge track, directly adopts the canny operator inside opencv here;

(4) Gabor wavelet feature extraction: point 5 40,8 directions of yardstick Feature Descriptors; PCA dimensionality reduction is adopted to tie up to 100; Gabor function can extract relevant feature on frequency domain different scale, different directions; Two-dimensional Gabor function can be expressed as:

$g_{uv}(x,y)=\frac{k^2}{{\mathrm{\σ}}^2}\exp (-\frac{k^2(x^2+y^2)}{2{\mathrm{\σ}}^2})\[\exp \left(ik\left(\begin{array}{c}x\\ y\end{array}\right)\right)-\exp (-\frac{{\mathrm{\σ}}^2}{2})\]$

Wherein: $k_v=2^{-\frac{v+2}{2}}\mathrm{\π},$

Choose the Gabor base in one group of different scale and direction and input fibre image carried out convolution, specifically choose 4 yardsticks (v=0,1 ..., 3), 8 directions (i.e. K=8, u=0,1 ..., 7), totally 32 Gabor kernel functions;

(5) characteristic vector is inputted classifier calculated result; It is scaled 48*48 size by unified for each fibre image of input, then extracts the Gabor characteristic collection of illustrative plates under 32 yardsticks, extract 48*48*32=73728 dimensional vector altogether; We take PCA method that original high dimensional data is down to 100 dimensions further, as the input feature value of SVM;

Described model learning flow process, is to obtain a grader, takes a kind of sorter model based on SVM, comprise the following steps:

(1) premise of model learning is the data base of the substantial amounts of woollen and cashmere of accumulation;

(2) on this basis, adopt the mode of artificial mark, make kind and the location of machine hard objectives fiber, be a kind of supervised learning mode;

(3) fibre image in data base being carried out pretreatment, feature extraction, this step is consistent with (2) (4) step of ONLINE RECOGNITION flow process;

(4) learning process takes the SVM classifier of two classification, and utilizes the libSVM increased income to be trained, and chooses RBF Radial basis kernel function, and iterations is set to 100000 times, iteration ends deviation 0.001.