Fingerprint feature identification

Abstract

Biometric identification systems have been developed to achieve automatic identification of a person based on ones physiological or behavioral characteristics. Biometric systems are critical in a wide range of applications such as banking system, e-commerce, smart cards, and access control to secure systems. Automatic fingerprint identification is one of the most reliable biometric systems, which is used for identifying persons. In this thesis the objective is to design a fingerprint identification system, which is capable of identifying a fingerprint with high level of accuracy. Therefore, this system can be applied to a wide range of forensic applications. Fingerprint identification being one of the most popular biometric techniques used in automatic personal identification. Many different kinds of fingerprint identification systems have been developed. Most of these systems based on the comparison of minutiae like ridge ending, ridge bifurcation etc. However, some noise like scratch will interrupt the accuracy of the matching result. Therefore throughout many years of studies, a number of algorithms and methods to extract the minutiae features of fingerprint are generated. Neural network is one of the best ways to undergo pattern reorganization since it has the capability to learn by itself. With the help of this algorithm, minutiae features of a fingerprint can be identified and greatly reduce the side effect of noises like scratch, which will interrupt the accuracy of the result.