Fast Palmprint Authentication by Sobel Code Method

The ideal real time personal authentication system should be fast and accurate to automatically identify a person's identity. In this paper, we have proposed a palmprint based biometric authentication method with improvement in time and accuracy, so as to make it a real time palmprint authentication system. Several edge detection methods, wavelet transform, phase congruency etc. are available to extract line feature from the palmprint. In this paper, Multi-scale Sobel Code operators of different orientations (0, 45, 90, and 135) are applied to the palmprint to extract Sobel-Palmprint features in different direc-tions. The Sobel-Palmprint features extracted are stored in Sobel-Palmprint feature vector and matched using sliding window with Hamming Distance similarity measurement method. The sliding win-dow method is accurate but time taking process. In this paper, we have improved the sliding window method so that the matching time reduces. It is observed that there is 39.36% improvement in matching time. In addition, a Min Max Threshold Range (MMTR) method is proposed that helps in increasing overall system accuracy by reducing the False Acceptance Rate (FAR). Experimental results indicate that the MMTR method improves the False Acceptance Rate drastically and improvement in sliding window method reduces the comparison time. The accuracy improvement and matching time improvement leads to proposed real time authentication system.