An enhanced method for singular points detection in fingerprint images

Abstract

The detection of singular points (SP), the core and delta points is an important step for automatic fingerprint identification system (AFIS). The number and location of singular points, are used to classify fingerprint images into five general groups; and therefore to narrow down the search space in large fingerprint databases. This paper proposes a new hybrid scheme to detect singularity points in a fingerprint image. We have enhanced the conventional Detection of Curvature (DC) and Poincare Index (PCI) methods for hybridization. Experiments indicate that the hybrid technique performs better than each algorithm individually. It demonstrates that the hybrid method is an effective and efficient scheme to detect singular points.