Face recognition method based on Gabor wavelet transform and local binary pattern (LBP) optimization

Abstract

The invention relates to a face recognition method based on Gabor wavelet transform and local binary pattern (LBP) optimization. Two-dimensional Gabor wavelet transform can associate pixels of adjacent areas so as to reflect the change conditions of image pixel gray values in a local range from different frequency scales and directions. The feature extraction and the classification recognition are carried out on the basis of a face image two-dimensional Gabor wavelet transform coefficient. For a high-dimensional Gabor wavelet transform coefficient, overall histogram features are extracted by adopting the LBP, and then the image is blocked by utilizing priori knowledge to extract the features of each piece of LBP local histogram. The method has better recognition rate, better robustness to illumination and wide using prospect in the fields of biometric recognition and public security monitoring.

Description

technical field

[0001] The invention belongs to the fields of image processing, biological identification technology, pattern recognition technology and computer vision, relates to Gabor wavelet transform and local binary pattern algorithm, in particular to a face recognition method based on Gabor wavelet transform and local binary pattern optimization. Background technique

[0002] With the continuous development of modern society and the continuous advancement and perfection of technology, people pay more and more attention to personal identity authentication, and people need to prove their identity almost all the time. For such a problem that can be encountered every day, various identification devices have emerged as the times require. For example: to take an exam, you must show your valid certificate, and to withdraw money from a bank, you must have a credit card and its matching password. Today, with the rapid development of electronic information technology, e-commer...

Examples

Embodiment 1

[0064] Embodiment one: the present embodiment is based on Gabor wavelet transform and local binary pattern optimized face recognition method, see figure 1 , the fusion of Gabor wavelet transform and local binary algorithm not only solves the problem of high-dimensional transformation coefficients after Gabor wavelet transform, but also directly solves the problem of difficult feature extraction in the face of high-dimensional data. The specific operation steps are as follows:

[0065] 1) Intercepting the pictures in the sample library or the pictures to be identified;

[0066] 2) Use Gabor wavelet to process the intercepted picture to obtain wavelet coefficients of different scales and directions;

[0067] 3) Take the modulus of the wavelet coefficients of different scales and different directions to obtain the response about the amplitude;

[0068] 4) Transform the above-mentioned wavelet coefficient images of different scales and directions with the LBP operator;

[0069]...

Embodiment 2

[0071] Embodiment 2: This embodiment is basically the same as Embodiment 1, and the special features are as follows

[0072]Described step 1) the method for intercepting the picture in the sample library or the picture to be identified is:

[0073] The faces in the face sample library are processed manually or automatically, and the original face image is required to have no less than 60 pixels between the eyes; the upper edge of the intercepted face image is located above the eyebrows, the area below the hairline, and the lower edge is located at the lips Below, above the chin, the left and right margins are located between the ear and the cheek; the resolution of the normalized image to the same scale is usually 64×64.

[0074] Described step 2) process the picture after intercepting with Gabor wavelet, obtain the wavelet coefficient of different scales and different directions, its method is:

[0075] Using the texture features of 8 directions, since the direction scale of...

technical field

[0001] The invention belongs to the fields of image processing, biological identification technology, pattern recognition technology and computer vision, relates to Gabor wavelet transform and local binary pattern algorithm, in particular to a face recognition method based on Gabor wavelet transform and local binary pattern optimization. Background technique

[0002] With the continuous development of modern society and the continuous advancement and perfection of technology, people pay more and more attention to personal identity authentication, and people need to prove their identity almost all the time. For such a problem that can be encountered every day, various identification devices have emerged as the times require. For example: to take an exam, you must show your valid certificate, and to withdraw money from a bank, you must have a credit card and its matching password. Today, with the rapid development of electronic information technology, e-commer...

Examples

Embodiment 1

[0064] Embodiment one: the present embodiment is based on Gabor wavelet transform and local binary pattern optimized face recognition method, see figure 1 , the fusion of Gabor wavelet transform and local binary algorithm not only solves the problem of high-dimensional transformation coefficients after Gabor wavelet transform, but also directly solves the problem of difficult feature extraction in the face of high-dimensional data. The specific operation steps are as follows:

[0065] 1) Intercepting the pictures in the sample library or the pictures to be identified;

[0066] 2) Use Gabor wavelet to process the intercepted picture to obtain wavelet coefficients of different scales and directions;

[0067] 3) Take the modulus of the wavelet coefficients of different scales and different directions to obtain the response about the amplitude;

[0068] 4) Transform the above-mentioned wavelet coefficient images of different scales and directions with the LBP operator;

[0069]...

Embodiment 2

[0071] Embodiment 2: This embodiment is basically the same as Embodiment 1, and the special features are as follows

[0072]Described step 1) the method for intercepting the picture in the sample library or the picture to be identified is:

[0073] The faces in the face sample library are processed manually or automatically, and the original face image is required to have no less than 60 pixels between the eyes; the upper edge of the intercepted face image is located above the eyebrows, the area below the hairline, and the lower edge is located at the lips Below, above the chin, the left and right margins are located between the ear and the cheek; the resolution of the normalized image to the same scale is usually 64×64.

[0074] Described step 2) process the picture after intercepting with Gabor wavelet, obtain the wavelet coefficient of different scales and different directions, its method is:

[0075] Using the texture features of 8 directions, since the direction scale of...

Images