Abstract

A fingerprint is an impression or mark made on a surface by a persons fingertip, able to be used for identifying individuals from the unique pattern of whorls and lines on the fingertips. Law enforcement have been using fingerprints to identify criminals from the latent impressions left behind at crime scenes. But some criminals escape from the cases by physically deforming their prints. With existing software, which searches through millions of fingerprints, spotting anomalies can be nearly impossible. Neural network is a nonlinear mapping system whose structure is loosely based on principles of real brain. The ability of the ANN to learn given patterns makes them suitable for applications like Fingerprint recognition. ANN can play a critical role. An ANN can be configured and trained to handle such variations observed in the texture of the fingerprint. The problem of automatic detection of alterations based on analyzing ridge orientation field and minutiae distribution is proposed here. Demonstration has been made in the MATLAB background. In the task of fingerprint recognition, the experiments conducted on various fingerprint images shows enhancement of performance

Paper Details