Personal Authentication-Based Fingerprint Recognition

Abstract

As our society has become more and more electronically connected and more proxy representations of identity such as passwords cannot be trusted to establish a person’s identity, biometrics offers a natural and reliable solution to certain aspects of identity management by utilizing fully automated or semi-automated schemes to recognize individuals based on their inherent physical and/or behavioral characteristics. Human fingerprints contain details called minutiae, which can be used as identification marks for fingerprint verification. The main goal is to develop a fingerprint verification system through extracting and matching minutiae. To extract good minutiae from fingerprints, preprocessing is applied in the form of image enhancement and binarization on fingerprints prior to their evaluation. Many techniques have been combined to build a minutia extractor and a minutia matcher. This system is capable of finding the correspondences between input pattern and the stored template pattern without resorting to exhaustive search. Evaluation of the developed system is done over a database with fingerprints from different people.