Comparative Study of Various Techniques of Fingerprint Recognition Systems

Abstract

Nowadays Biometric plays vital role in many applications. It is defined as the credentials of people based on their physiological or behavioral characteristics. Biometric recognition can be classified into various types they are fingerprint, face, iris, palm print, voice, and DNA recognition. Among these fingerprint recognition plays major role since it do not change due to age factors, bruises cut, weather factor and so on. Various matching techniques used for fingerprint recognition systems such as minutiae based matching, pattern based matching, Correlation based matching, and image based matching. This paper focuses on features extraction and minutiae matching stage. Two fingerprint recognition regimes have been developed based on minutiae matching, the first one is: Artificial Neural Network based on Minutiae Distance Vector (ANN-MDV), while the other one is: Artificial Neural Network based on Principle Component Analysis (ANN-PCA). It is observed that the recognition rate is increased and return better results. A comparative study among the various recognition systems is done based on Average Recognition Time (ART), False Acceptance Rate (FAR), False Rejection Rate (FRR), and the accuracy of the system. The experimental results are done on FVC2002 database using Matlab 7.10.0 (R2010a). The results show that the ANN-PCA system has the highest system accuracy (98%), lowest FAR, lowest FRR, and acceptable average recognition time. Therefore ANN-PCA is the best recognition system. Also the experimental results show that ANN-MDV system has shortest ART (0.251).