Fingerprint Singular Point Detection Competition

Automatic biometric identification based on fingerprints is still one of the most reliable identification methods in criminal and forensic applications. Fingerprint images are directionally oriented patterns formed by ridges and valleys that can be captured from a finger with a multitude of sensors, particularly, capacitive, optical, thermal sweeping and ultrasonic. Fingerprints are unique to each individual and have been widely used for biometric identification. A critical step in fingerprint analysis without human intervention is to automatically and reliably extract singular points from the input fingerprint images. The singular points - cores and deltas - are the most important topological features of a fingerprint. The singular point area is defined as a region where the ridge curvature is higher than normal and where the direction of the ridge changes rapidly. These singular points not only represent the characteristics of local ridge patterns but also determine the topological structure (i.e., fingerprint type).