Latent Fingerprint Matching

Latent fingerprint identification is of critical importance in forensics. While tremendous progress has been made in the field of automatic fingerprint identification, latent fingerprint matching continues to be a difficult problem because the challenges involved in latent print matching are quite different from rolled (full) fingerprint matching. Poor quality of friction ridge impressions, small finger area and large non-linear distortion are the main factors that affect latent fingerprint matchers. We propose a system for matching latent images with full fingerprints that uses minutiae as well as ridge information as the discriminative features. We have developed a minutiae-based fingerprint matcher that takes into account the specific characteristics of the latent matching problem. The ridge correlation matcher determines the degree of similarity in the ridge flow patterns of latents and full-print images. Experimental results on the NIST Special Database-27 which con...

• Type: Journal
• Year: 2011
• Where: PAMI
• Authors: Anil K. Jain, Jianjiang Feng
• Keywords: Latent fingerprint, Operations Research, PAMI 2011, Ridge, fingerprint Matcher