Pre-processing And Feature Extraction Algorithms Research Of Palmprint Recognition

With the fast development of computer and internet, people's entertainment and economic activities have close relationship with computer and 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. However, biometrics based on personal biologic feature can solve the authentication problems efficiently and safely, which is concerned widely.Biometrics combines biology technology and information technology to exploit physical features in human body such as fingerprint, iris, face and palmprint or behavioral features such as gait and signature to identify a person. Now it is considered as the highest-ranking security key system in the highly interconnected information society. This new technology can be applied to homeland security, social welfare, financial and e-commerce, and it is becoming the highest potential technology in this era.Today, with the rapid development of information and internet all over the world, information security is extraordinarily important, especially, personal identification technology. Because biological feature identification technology has unique stability, uniqueness and convenience, it is applied more and more broadly.The palmprint recognition is a new biometrics technology, which use palm texture as biologic characters to recognize identity. 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. We first propose an efficient algorithm of region of interest extraction for palmprint images. And we also propose several efficient algorithms of palmprint feature extraction. In detail, this dissertation concentrates on the research of the following key1. Discuss the meaning, history, developing and the state of biometric and palmprint recognition. 2. Propose an efficient method obtaining the ROI (region of interest), based on the research of palmprint image pre-processing technology: firstly, a global threshold is used to binarize the original palmprint image, and the edge of the palm is extracted. Then, a new coordinate system is established according to the slope making by the two gaps between the first and middle fingers, the ring and little fingers, and the centre of the palm. Finally, a fixed 128×128 subimage is extracted as ROI.3. Summarize some feature extraction methods of the palmprint recognition; represent the differences between the weighted PCA and the traditional PCA, and show that the former method has higher recognition rate than the later one for the reason of weighted PCA method weakens the feature vector related with illumination in the case of that the illumination has great impact on palmprint image; compare the recognition rate of the LDA and PCA, and conclude that the performance of LDA is better than PCA in the case of small training set.