A Mobile Phone Palmprint-based Authentication System

Biometric technology is one of the hot focuses on academic research and practical security application, and plays more and more important role in society lives. Palmprint recognition and verification has wide application foreground for the reason that it is considered to be a non-invasive, low cost, and natural biometric technology.Mobile phone is coming into people's every lives as communication tool. And the functions and services of mobile phone are getting more and more abundant, and this brings forward the high security demand of mobile phone. This thesis deals with palmprint recognition and development of a palmprint recognition and verification system. The main contents of the thesis are listed as follows:1. Based on the requirements and functional analysis of the system, the workflow and functional modules of the system are determined. Then the palmprint authentication system's scheme of enrollment, verification, setting are designed and the development and testing platform and are implemented.2. Palmprint image preprocessing technologies are studied, including the algorithm of ROI (Region of Interest) and gray preprocessing. The geometric normalization technique and the photometric normalization technique for system are made certain.3. Merit and shortcoming of current palmprint recognition technologies are discussed. I choose Fisherpalm to be the algorithm of system. And Gabor wavelet is selected to enhance the robust to lighting variations and efficiency. The principle of this algorithm is introduced in detail. Functions of the algorithm are tested using the proposed evaluation criterion. The experimental results show that the proposed algorithm provides better performance compared. And the palmprint recognition algorithm is tested on mobile phone. The experimental results indicate the algorithm gets a good performance in palmprint recognition. In the development of system, the palmprint recognition algorithm is predigested because of the shortage of mobile phone.4. A palmprint recognition and authentication system is developed on mobile phone, and it provides the function of palmprint orientation, palmprint image preprocessing, feature extracted, user enrollment, user verification and threshold setting. Then the system is tested in palmprint database and real-life application environment. The experimental results show that the system approaches high recognition rate (EER<7%).