A personal identification is needed in a wide range of application domains. Fingerprint identification, as one of biometric technologies, is being widely used in forensics and civilian application areas. It has attracted more and more researchers' attention because it is more reliable relative to traditional methods such as ID and passwords. In this paper, we proposed a minutia matching algorithm which modified Jain et al.'s algorithm. Not the minutiae themselves but those around them are used to compose feature vectors, so our algorithm can better distinguish two images from different fingers and is more robust to nonlinear deformation. Further more, we introduce a enhancement method which is more faster, so our AFIS(Automated Fingerprint Identification System) can be used in real-time system. We had designed some fingerprint-based biometric system such as system for checking on work attendance and WINDOWS logon system.
修改评论