Automatic Fingerprint authentication for personal identification and verification has received considerableattention over the past decades among various biometric techniques because of the distinctiveness andpersistence properties of fingerprints. Now fingerprints are set to explode in popularity as they are beingused to secure smart phones and to authorize payments in online stores. The main objective of this paper isto review the extensive research work that has been done over the past decade and discuss the variousapproaches proposed for fingerprint matching. The proposed methods were based on 2D correlation in thespatial and frequency domains, Artificial Neural Networks, Hough transform, Fourier transform, graphs,local texture, ridge geometry etc. All these different techniques have their pros and cons. This paper alsoprovides the performance comparison of several existing methods proposed by researchers in fingerprintmatching.
展开▼