Font Size: a A A

The Identification Research Of Identity Recognition Based On Face And Fingerprint

Posted on:2007-12-02Degree:MasterType:Thesis
Country:ChinaCandidate:B GouFull Text:PDF
GTID:2178360185978225Subject:Communication and Information System
Abstract/Summary:PDF Full Text Request
Traditional personal identification methods can not satisfy our demand with the development of modern information society. Biometrics is a kind of science and technology for personal identification. It provides a highly reliable and robust approach to identity recognition and is playing a more and more important role in this field. Face and fingerprint personal identification systems are two convienent, reliable and stable identification ways which are widely studied and applied. However, the automatic personal identification system based solely on fingerprints or faces is often not able to satisfy people. Face recognition is fast but not reliable while fingerprint identification is reliable but with high computational cost. In this paper, a recognition system which integrates face recognition and fingerprint recognition is introduced. At first, it gets N candidates quickly depending on face recognition process.Then the system matches fingerprints in a small part of the sample database corresponding to the N candidates. As a result, this system overcomes the limitations of both methods while developing their advantages.This paper mainly deals with face and fingerprint recognition process using face and fingerprint features abstracted by others. Including: (1) A face recognition algorithm using support vector machines is introduced. The SVM training time is reduced dramatically owing to a fast SVM training method which gets support vectors in advance and then uses an iterative and circulative strategy for training. (2) A twice fingerprint matching algorithm is introduced. The first fingerprint matching process matches the local feature vectors. It works imitating fingerprint experts. In this phase an algorithm used to distinguish the best matching pair is introduced. Then the second fingerprint matching process matches the global feature vectors after the first matching process. A...
Keywords/Search Tags:\Multi-biometrics recognition, Human face recognition, Support vector machine, Fingerprint recognition
PDF Full Text Request
Related items