Palm print identification method based on contour and edge texture feature fusion

Abstract

The invention belongs to the technical field of the palm print identification, and relates to a palm print identification method based on contour and edge texture feature fusion. The method comprises the steps of firstly preprocessing an image, disintegrating a palm print image into an image contour and an image edge texture by utilizing average value filter, carrying out characteristic extraction by adopting a grey level histogram and differential box dimension, and finally carrying out matching by utilizing the universal chi-square distance. The method is simple, the principle is scientific, the identification time is short, the identification precision is high, the palm print can be identified in real time, and a quick and effective identification method is provided for the identity identification.

Description

Technical field: [0001] The invention belongs to the technical field of palmprint recognition, and relates to a palmprint recognition method based on fusion of outline and edge texture features. Background technique: [0002] At present, the identification technology based on biometric identification is an effective identification method with high reliability and stability. As an important biometric feature, palmprint recognition has attracted extensive attention from researchers due to its advantages of low cost, strong friendliness, and high recognition accuracy. Palmprint feature recognition technology, as an emerging technology in the field of biometric A large number of scientific research results have been obtained in more than ten years, and its development is very rapid. [0003] Palm prints contain rich texture information, including texture features of different thicknesses such as main lines, creases, and mastoid lines. These features are stable and unique. Using...

AI Technical Summary

Problems solved by technology

Because the main line and folds of different people are very different, Yuan Weiqi et al. ): 807-811) regard the palmprint grayscale image as a grayscale surface in three-dimensional space, and use the surface as a feature to match, calculate the variance through the difference in the larger texture, and then use the unevenness of the grayscale surface The algorithm uses the entire image for matching, and part of the palmprint information is lost. When the data gradually increases, the recognition rate will decrease; Chen Ziyi et al. (Chen Ziyi, Kang Wenxiong, Deng Feiqi. Based on the statistical analysis Palmprint line extraction[J].Computer Engineering and Design, 2011,32(2):653-670) using the gray difference statistics, by judging the gray value of the object point and the number of points in the continuous palmprint line point set, extracting Extract the binary image of the palm lines, and finally evaluate the extraction effect of the palm lines by the degree of membership. This algorithm has high complexity, and the recognition rate is low, which does not meet the real-time requirements.

The main line and folds are not all the information of the image, and the small texture of the mastoid lines with large fluctuations is also important information for distinguishing palm prints. Using the advantages of fractal for image processing with large fluctuations, Hong Danfeng et al. (D.Hong, Z.Pan, X.Wu.Improved Differential Box Counting with Muti-scale and Multi-direction:A new palmprint recognition method.Optik-International Journal of Light Electron Optics,2014,125(15):4154-4160) using fractal dimension as feature vector Extract the texture features of the image, and compare the local fractal and global fractal algorithms at the same time. It proves that the local fractal algorithm can easily find out the complex transformation area of ​​the image, but the complexity of the local fractal dimension algorithm is not conducive to medium and large data applications. ; Zhao Zhigang et al. (Zhao Zhigang, Wu Xin, Hong Danfeng, Pan Zhenkuan. GLBP palmprint recognition algorithm based on information entropy [J]. Computer Science, 2013,41(8):293-296) realized a multi-level algorithm using information entropy The described palmprint recognition method adds scale and direction information to make up for the inaccurate defect of single feature description; Pan X, Ruan Q, Wang Y. Palmprint Recognition Using Contourlets-based Local Fractal Dimensions. 2108-2111) proposed a palmprint recognition method based on the combination of Contourlet and local fractal. Although this method has a high recognition rate, it has initially solved the problem of scale direction, and combined with fractal dimension, it can effectively describe the roughness of image texture. , which provides a new idea for the palmprint recognition algorithm, but the algorithm complexity is high and cannot meet the real-time requirements

Images