An advanced scratch removal method for Fingerprint biometrics

Abstract

Minutiae extraction for automatic Fingerprint identification system is one of the most important steps however, the performance of minutiae extraction relies heavily on an enhancement algorithm. There are a lot of things that affect the quality of the fingerprint; one of them is scratches occurred in the fingerprint. Scratches generate the cutting in ridges. This affects the performance of the minutiae extraction. There are many algorithms for fingerprint enhancement, but very limited papers considering the enhancement by scratch removal in the fingerprint. In this paper we present a new effective method for making scratch free fingers. This proposed method can be used to detect and reduce the scratches in the fingerprint. The power of the proposed method is made by morphological operations and inpaint operations. Morphology concepts are used to detect the scratches and exemplar inpaint method is used to fill the scratched locations. Experimental results show a significant improvement of the fingerprint enhancement in the scratch-affected — area.