Direct Fingerprint Classification in Raw Fingerprint Images by Using Principal Gabor Basis Functions

Abstract

A fingerprint classification algorithm can speed up the processes of fingerprint identification and verification. Therefore, this algorithm must be performed fast and correctly. Because Gabor filters only have large responses with similar orientation and spatial-frequency, in this paper, we will use a group of principal Gabor basis functions to represent the ridge structures of core regions. Fingerprint patterns will have large responses only to the Gabor filter-based templates of the corresponding classes. Therefore, the classes of fingerprints are directly detected from gray-scale images and many pixel-level computations are not involved. As a result, a fast class-detection for fingerprints is achieved.