Biometric recognition using finger and palm vein images

In recent times, biometrics is the best alternative for the token-based and knowledge-based security systems. Out of the existing biometric modalities, the vascular biometric modalities are preferred for authenticating the person, because of its uniqueness among all individuals. This paper proposes a multimodal biometric system using vascular patterns of the hand such as finger vein and palm vein images. Initially, the input palm vein and finger vein images are pre-processed so as to make them suitable for further processing. Subsequently, the features from palm and finger vein images are extracted using a modified two-dimensional Gabor filter and a gradient-based techniques. These extracted features are matched using the Euclidean distance metric, and they are fused at the score level using fuzzy logic technique. The proposed technique is tested on the standard databases of finger vein and palm vein images. This method provides lower false acceptance rate, false rejection rate and high accuracy of 99.5% when compared with the existing techniques, indicating the effectiveness of the proposed system.