An efficient method for Finger-Knuckle-Print recognition based on information fusion

Information fusion of various biometrics for its high performance in biometric recognition system, has recently attracted much attention. So in this paper the information of biometrics in different aspects is considered. At the first, the information fusion in single modal is investigated. In this stage, two different subsets of feature vectors are extracted from each image and are serially combined. With this work a new vector with higher dimension is considered as feature vector of each image. The characteristic biometric used in this paper is Finger-Knuckle-Print (FKP) which is unique and is recently used for personal identity authentication. The database used in our experiment contains the images of four different fingers. Therefore at the second stage, the information fusion of each finger at feature level is investigated. In fact, this fusion works as a kind of multi-modal method with a single biometric characteristic but multiple units. Poly-U FKP database was used to examine the performance of the proposed method and the experimental results proved that combining the features of four fingers is able to increase the recognition rate compared to that produced by each finger, separability.