Overlapped Fingerprint Separation and Feature Enhancement Using Gabor Filter

Fingerprints are claimed to be both unique and permanent, making it an ideal biometric trait for person identification in. Fingerprint images generally contain either a single fingerprint or a set of non overlapped fingerprints. However, there are situations where several fingerprints overlap on top of each other. Overlapped images are mainly encountered in latent fingerprints lifted from crime scenes. Overlapping may also occur in lives can fingerprint images when the surface of fingerprint sensors contains the residue of fingerprints of previous users. In this paper, we propose a novel algorithm to separate overlapped fingerprints into component or individual fingerprints and evaluate it using both real overlapped latent fingerprints. The proposed method involves two basic assumptions which involve overlapped fingerprint is combination of two fingers and two fingerprints has different orientation. It first estimate the orientation field of the given image with overlapped fingerprints and then separates it into component orientation field using a relaxation labeling technique. Most Automatic Fingerprint Identification Systems (AFIS) use some form of image enhancement. Once the Finger print was extracted Gabor filtered can be used to enhance the quality of extracted image.