The utilization of a Taylor series-based transformation in fingerprint verification

摘要

Dealing with non-linear distortion in fingerprint images is a major difficulty for automated fingerprint verification systems. While this distortion can be a nuisance in minutiae matching systems, it is a major concern when matching smaller structures, such as points along ridges and pore locations. In this paper we show that a simple transformation derived from a Taylor series expansion can be used in conjunction with a set of corresponding minutia points to improve the correspondence of finer fingerprint details within a fingerprint image. This is demonstrated by applying the transformation to a database of fingerprint images and examining the ridge and pore match scores with and without the transformation. The results of our study show that this transform does provide a noticeable increase in matching accuracy.