Research On Palmprint Recognition Based On Image Quality Assessment

The palmprint identification technology, with its many merits including rich information of palmprint image, simple acquisition equipment and high acceptance and so on, has been a high-profile biometrics. It has intensively studied and widely applied in areas of police system, medical research and public welfare.With the development of non-contact palmprint acquisition system, the quality of the image becomes a problem which can not be ignored. The increasing of ease of use will reduce the quality of the image. In many factors, which affect the image quality, the defocus blur is a very important image distortion. And traditional blur palmprint recognition algorithms use the stable palmprint characteristic to recognize, so the recognition rate is low. Based on the introduction of palmprint image quality evaluation method, this paper proposes a palmprint recognition method based on LMCP(Local Multi-layer Contrast Pattern) and the log-Gabor data fusion. The main work is as follows:(1)This paper introduces palmprint image quality evaluation. The method is based on Daugman algorithm. Firstly, laplacian sharpening is used to sharpen the palmprint image. And then, it calculates the image quality score. At last, by setting a threshold, it distinguishes clear images and blurred images and removes serious blurred images.(2)This paper proposes a palmprint recognition method based on LMCP and log-Gabor data fusion. Firstly, it analysis the theory of LMCP operators and log-Gabor filter and experimental results show the effectiveness of the two methods. Secondly, we fulfill palmprint recognition through LMCP and log-Gabor data fusion. On the basis of extracting LMCP features and log-Gabor features, it finishes the matching degree value fusion of two features, and then uses K-nearest neighbor classifier to match and recognize palmprint. Simulation results of MATLAB format show that data fusion method makes the accuracy rate improved obviously.