Separating Overlapped Fingerprints Using Constrained Relaxation Labeling

Overlapped fingerprints are frequently encountered in latent fingerprints lifted from crime scenes. It is necessary to separate such overlapped fingerprints into component fingerprints so that existing fingerprint matchers can recognize them. The most crucial step in separating overlapped fingerprints is the separation of mixed orientation fields into component orientation fields. In this paper, a constrained relaxation labeling algorithm is proposed to perform the orientation field separation task. Experimental results on both real and simulated overlapped fingerprints show that the proposed algorithm outperforms the state-of-the-art algorithm in both accuracy and efficiency.