Research Of Fingerprint Verification

With the rapid Progress of computer science and network technique,An accurate,secure and practical techno1ogy of Personal identification becomes more and more important. Technology of Personal identification based on Biometrics has received extensive attention. Technology of Fingerprint recognition is the earliest one and is app1ied widely in the all techniques of biometrics recognition, Then is taking full advantage of the universality, uniqueness and permanency of the fingerprint, and gradually has taken place of traditional identification method that is based on symbol and number. Nowadays the technology of fingerprint identification is fully used in network, bank, finance, insurance and security.This paper research the basic principles and process of the fingerprint identification system,and focus on the pre-processing algorithms of fingerprint image and finally verify.Firstly, aiming at conglutination of ridge line and inhomogeneous transition in all directions in the traditional filter template, then proposed symmetrical filter template algorithm ,the method used rotate the filter template of circular diameter to equal filtering effect in different directions, corrected the orientation of ridge line, removed conglutination of ridge line, and separated the ridge from the valley clearly.Secondly, this paper study deeply improved opta algorithm,aiming at incomplete thinning and many burrs, used improved elimination of templates, removed burrs of the horizontal direction effectively; proposed changeable template and correcting template, the changeable template eliminate the vertical direction of the burr, correcting template made the bifurcation point thoroughly and eventually figured out smooth fingerprint image .Finally, this paper study elimination of false minutiae in process of the fingerprint identification, aiming at extracting border points as the feature points in the process of extracting minutiae, this paper proposed judge of border information and eliminated effectively border minutiae.The test images prove the validity of the methods.