Personal Verification Through Finger Vein Pattern Recognition Using Support Vector Machine

Biometric based personal verification gains popularity due to the importance of security and privacy protection. The target of this paper was the design and development of a finger vein identification system that could be used by a number of users in an Automated Teller Machine (ATM) environment. Finger vein recognition uses the internal and unique patterns of finger veins to identify individuals at a high level of accuracy. In general, it is identified that it is a great challenge to design a finger vein identification systems that provides a certain level of performance. For this purpose an effective algorithm based on Support Vector Machine (SVM) for finger vein recognition is used. The information of the finger veins extracted based on a Local Binary Pattern (LBP) and Wavelet Transform. Finally, the two score values by the LBP and Wavelet transform is to be combined by the Support Vector Machine (SVM) for image classification. The technique is implemented in MATLAB platform. The Equal Error Rate (EER) and the processing time is reduced when compared to other methods.