FINGER PRINT IMAGE RECOGNITION

Abstract

Fingerprints are imprints formed by the friction ridges of the skin and thumbs. Fingerprints are the oldest and most widely used form of biometric identification. However manual fingerprint recognition is so tedious, time consuming and expensive that is incapable of meeting today’s increasing performance requirement. An automatic fingerprint image recognition system is widely accepted in many applications such as building or area security. Contrary to popular belief and despite decades of research, reliable fingerprint image recognition is still an open problem. The aim of this project is to develop the fingerprint image recognition system. The aim is divided into 3 major steps of image enhancement, feature extraction and feature matching. A comparison of the enhancement techniques available in various literature lead to the five sub-stages in the enhancement i.e. histogram-equalization, normalization, fft-enhancement, binarization and noise filtering. Minutiae-based matching is employed in this project. This technique is based on the extraction of minutiae using crossing number approach from the thinned, binarized and segmented version of a fingerprint image. Then real minutiae set of the two images are matched to take the decision in Identification and Verification. Also a program coding with MATLAB going through all the stages of the fingerprint recognition is built. It is helpful to understand the procedures of fingerprint recognition. And demonstrate the key issues of fingerprint recognition. The aim of the experimental results section is to illustrate the results of each stage in the enhancement algorithm and to assess how well each stage performs. vi