Improved Algorithm for Separating Latent Overlapped Fingerprints

Latent Overlapped fingerprints are frequently encountered in latent fingerprints lifted from crime scenes. Overlapping occurs when the same location of an object is touched by one or more fingers several times. It is necessary to separate such latent overlapped fingerprints into component fingerprints so that existing fingerprint matchers can recognize them. In fact, fingerprint examiners usually do not collect latent overlapped fingerprints since they are too complicated to process. Thus it is desired to develop an algorithm to separate the overlapped fingerprints into individual fingerprints in order to reduce the labour of fingerprint examiners. A new approach for separating latent overlapped fingerprints are proposed to improve the perfection of the separating algorithms by overcoming the difficiency in principal component analysis (PCA) technique. A new method provides robustness and efficiency to the system.