AUTOMATIC LATENT FINGERPRINT SEGMENTATION BASED ON ORIENTATION AND FREQUENCY FEATURES

Latent fingerprints are lifted from crime scenes in a routine procedure that is extremely important to forensics and law enforcement agencies. Since it contains as small regions of fingerprint, latents have a significantly smaller number of minutiae points compared to full (rolled or plain) fingerprints. The small number of minutiae and the noise characteristic of latents make it extremely difficult to automatically match latents to their mated full prints that are stored in law enforcement databases. To overcome this problem, the automatic segmentation is used. An important step in an automatic fingerprint recognition system is the process of automatically segmenting the fingerprint images. In this paper, the segmentation process consists of the three blocks namely (i) segmentation of Orientation feature, (ii) Segmentation of Frequency feature and (iii) Post processing. The Orientation Feature process is used to obtain the fingerprint ridge orientations, the Frequency Feature process is used to obtain the local ridge frequencies of the fingerprint. The Post Processing method combine these two results to find the candidate fingerprint regions (foreground).The proposed scheme achieves accurate segmentation for latent matching of fingerprint. This system improves the accurate segmentation of foreground and background regions from latent fingerprint images. This system gives 77% of accuracy to detect a foreground region from latent fingerprint images.