Fingerprint image enhancement using GWT and DMF

Fingerprint image enhancement is an essential preprocessing step in fingerprint recognition applications. In this paper we introduce an approach that extracts simultaneously orientation and frequency of local ridge in the fingerprint image by Gabor wavelet filter bank and use them in Gabor Filtering of image. Furthermore, we describes a robust approach to fingerprint image enhancement, which is based on integration of Gabor Filters and Directional Median Filter(DMF). In fact, Gaussian-distributed noises are reduced effectively by Gabor Filters and impulse noises by DMF. the proposed DMF not only can finish its original tasks, it can also join broken fingerprint ridges, fill out the holes of fingerprint images, smooth irregular ridges as well as remove some annoying small artifacts between ridges. Experimental results show our method to be superior to those described in the literature.