Research On Technology For Palmprint Recognition

With the fast development of computer and internet, People's entertainment and economic activities have close relationship with compute randy internet, and the whole society run more and more depending on network. The security mechanisms of confidential information protecting need to be strengthen continuously. Traditional security and authentication can not guarantee the safety of authentication.The palmprint recognition is a new biometrics technology, which use palm texture as biologic characters to recognize identity. Due to its hard copy or counterfeit features, and can solve the authentication problems efficiently and safely, which is concerned widely. As palmprint is typical of ease acquisition, and its major feature is apparent, stability and divisibility, palmprint automatic identification is a very potential identification technology.According to the characteristic of palmprint, the dissertation concentrates on the research of the key technologies. Proposed palmprint image preprocessing, feature extraction, feature recognition and other related aspects of the new algorithm. In detail, this dissertation concentrates on the research of the following key.We first propose an effective algorithm of region of interest extraction for palmprint images: First of all, gray stretch of the original image, enhanced image contrast, and then use Roberts operator the outer contour extraction of palm; then identify two key points, connecting on two key points, and then take that last point as the center in order to extract a 128x128 region of interest.Secondly by comparing the improved Sobel operator and Sobel operator is proposed based on the improved Sobel operator and the single-threshold algorithm combined with the main line on the palm extraction, and the use of Gabor filters with the fast Fourier transform to extract palm ridge energy and as the characteristics of palmprint images.Thirdly introduce the principle of BP neural network, BP network used in this paper, the structural design and training, and network with BP features of the palmprint recognition.