A Minutia Detection Approach from Direct Gray-Scale Fingerprint Image Using Hit-or-Miss Transformation

Abstract

Personal authentication through fingerprint matching merely depends on the proper identification of the minutia points of a fingerprint. In this paper, a minutia detection scheme is presented by employing gray scale hit-or-miss transformation. The work focuses exclusively on two widely used minutia points namely ridge bifurcations and ridge endings. To detect all the minutia points, a set of bifurcation shaped templates, oriented along various directions, are constructed. Ridge bifurcations are identified directly from original fingerprint through hit-or-miss transformation using the predefined templates. The ridge endings, on the other hand, are detected from the inverted image by using the same set of templates. The proposed method is implemented and tested on real fingerprint images. The experimental results show the efficiency and accuracy of the method. A comparative study is also provided between the proposed method and other relevant techniques which proves the efficacy of the method.