The Research Of Fingerprint Image Preprocessing And Minutiae Extraction Algorithm

In recent years,more and more occasions require the identity authentication with the continuous growth of e-commerce and information security needs.Among them,the fingerprint identification technology has become the most widely and effective means of identity authentication due to its convenience,high accuracy and low cost.However,most of the core technology wouldn't be publicized because of the commercial benefits,at the same time the higher performance is required because of social development,so the research on this field still has the important theoretical significance and practical value.Fingerprints are scraggly lines on the tip of fingers,which have the characteristics of unique and stability.The automatic fingerprint identification system(AFIS) is a synthetical system that integrates photovoltaic technology,image processing,computer and network, database technology and pattern recognition technology.In the view of the operation of the AFIS,and on the basis of conclusion of the existing research results,this paper study on the key technology in the fingerprint image pre-processing and feature extraction algorithm,and make some improvements:in the fingerprint image pre-processing,using an adaptive image enhancement algorithm,according to whether the neighborhood have the bifurcation point, respectively using different filters for image enhancement and achieved a better effect.According to the problems in OPTA thinning algorithm,this paper make some improvement on the algorithm and after treatment the fingerprint ridge smoother.On the feature extraction stage,study and realize the algorithm of the 8-neighbor-based ridge tracking code for minutiae extraction,and then use integrated post-processing rules to eliminate different types of false minutiae in fingerprint thinned image.