Meandering energy potential to locate singular point of fingerprint

Abstract

Singular point is the location of high curvature area of a fingerprint. It represents the global characteristic and is quite useful for fingerprint classification and matching. Despite being a very important feature, the localization of the singular point is still not perfect. This paper proposes a novel algorithm to locate prominent singular points from a fingerprint image by devising the concept of meandering energy potential (MEP). One of the advantages of the proposed algorithm is that it does not require any prior knowledge on the fingerprint structure. Experimental results have been obtained on a widely used publicly available fingerprint database FVC2002. The proposed algorithm has significantly high accuracy as compared to any other state-of-the-art methods in the literature.