A robust algorithm for fingerprint core-point detection

This paper proposes a robust algorithm to detect fingerprint core-points. Our proposed approach takes into account the region of interest and local orientation features of fingerprints. The algorithm coarsely detects the core-point and restricts our search space to a smaller region, following which, the existing Geometry of Region technique is used to detect the core-point to a finer extent. The method was verified using the FVC - 2002 dataset and marked reduction in the misdetections was noted.