Minutiae Feature Extraction from Fingerprint Images

Abstract

This paper presents a reliable method of computation for minutiae feature extraction from fingerprint images. We present a novel fingerprint representation scheme that relies on describing the orientation field of the fingerprint pattern with respect to each minutia detail. A fingerprint image is treated as a textured image. Improved algorithms for enhancement of fingerprint images, which have the adaptive normalization based on block processing, are proposed. An orientation flow field of the ridges is computed for the fingerprint image. To accurately locate ridges, a ridge orientation based computation method is used. After ridge segmentation a method of computation is used for smoothing the ridges. The ridge skeleton image is obtained and then smoothed using morphological operators to detect the features. A post processing stage eliminates a large number of false features from the detected set of minutiae features. A fingerprint matching algorithm, based on the proposed representation, is developed and tested with a series of experiments conducted on collections of fingerprint images. The results reveal that our method can achieve good performance on these data collections.