On matching altered fingerprints

Fingerprint alteration refers to changes made in a person´s finger ridge structure by means of abrading, cutting, or performing plastic surgery on the fingertips. Fingerprint alteration is a serious attack on Automated Fingerprint Identification Systems (AFIS) since it can reduce the similarity between fingerprint impressions from the same finger due to the loss of genuine minutiae, increase in spurious minutiae and distortion in spatial distribution of the minutiae. We investigate the capability of a state-of-the-art commercial fingerprint matcher to match altered fingerprints to their pre-altered mates by removing spurious minutiae in the altered region. We also attempt to restore minutiae structure in a well-known type of fingerprint alteration, called `Z´-cut, which tears local skin patches of a finger and switches them with each other. Nonrigid skin distortion introduced during switching of local patches is modeled by thin-plate spline (TPS). Experimental results show that removing spurious minutiae in the altered region and relocating the minutiae in the restored local patches improve the matching performance and help to retrieve correct mates from a large background fingerprint database.