A novel approach for Finger-Knuckle-Print recognition based on Gabor feature fusion

One of the newest biometric identifier, which is recently used for personal identity authentication, is Finger-Knuckle-Print (FKP). In this paper, we present a novel method for personal identification and identity verification which includes Gabor filter bank, combination of PCA and LDA algorithms and Euclidean distance measure. These three steps are used for feature extraction, dimensionality reduction and the classification stage, respectively. Also the information fusion at feature level is used for different combination of fingers to improve the recognition rate. In the other hand, here this algorithm works as a kind of multi-modal method with a single biometric characteristic but multiple units. Poly-U Finger-Knuckle-Print database is used to examine the performance of the proposed method. The result of identification and verification experiments by combining the features of four fingers are obtained, 98.79% and 91.8%, respectively, which demonstrate the efficiency and effectiveness of this new biometric characteristic.