ABSTRACT

Fingerprint-based identification is one of the core methodologies for person identification. It remains a reliable, efficient and commonly accepted biometric. The most popular and extensively used method for fingerprint identification; the minutiae based, show poor performance for real time authentication. However, the performance of minutiae based approaches can be boosted by combining statistical information obtained from other image processing techniques (Wavelet transforms). This paper explores hybrid fingerprint matching system with the fusion of minutiae features and wavelet statistical features. The final matching score is calculated by fusing matching scores of the minutiae based method and wavelet based method. The performance of the proposed hybrid fingerprint recognition method can be evaluated by measuring its False Reject Rate (FRR) and False Accept Rate (FAR) as shown in the simulation results. The proposed method is more efficient than conventional minutiae based methods for real time authentication systems with large size databases.