Robust Reference Point Detection Using Gradient of Fingerprint Direction and Feature Extraction Method

Abstract

A novel reference point detection method is proposed by exploiting the GPM(Gradient Probabilistic Model) that captures the curvature information of fingerprint texture. The detection of reference point is accomplished through searching and locating the points of occurrence of the most evenly distributed gradient in probabilistic sense. We also propose a novel filterbank method to improve shortcoming of existing filterbank method in verification part. Existing filterbank method can lose the discerning attributes because the sectors of the outer band from the reference point are larger in size than those of the inner bands. Such shortcomings of the filterbank method are resolved by maintaining the attribute regions to equal size.