Edge Detection Method for Latent Fingerprint Images Using Intuitionistic Type-2 Fuzzy Entropy

A latent fingerprint is an interesting issue because of it has attained from crime places and moreover contained a low quality image, less number of features and unwanted noises. It is necessity to extract the original image with exact boundary from the surface for further processing such as authentication, identification and matching. In this work, a new distance measure has been proposed for latent fingerprint edge detection using Intuitionistic Type-2 Fuzzy Entropy (IT2FE) and a comprehensible definition is made for Intuitionistic Type-2 Fuzzy Sets (IT2FS). IT2FS takes into account of uncertainty in the form of membership function which is also termed as Intuitionistic Type-2 Fuzzy Divergence (IT2FD). The experiment is conducted with public domain fingerprint databases such as FVC-2004 and IIIT-latent fingerprint. The edge detection is carried out with the proposed method and the results are discovered better regarding existing method.