Multi-modal biometric system using palm print and palm vein features

Muti-modal biometric recognition systems have attracted the attention of many researchers in today´s modern world. These systems have greater advantages over traditional systems that are difficult to break and provide good anti-spoofing abilities. Use of these systems has increased in recent years owing to the increasing trend of thefts, breaking of security systems, hacking and another means of unauthorized access. In this paper a multimodal recognition algorithm using palm print and palm vein images. The palm print image is rich in line features as it consists of wrinkles, ridges and principal lines. On the other hand the palm vein image contains rich texture features in the form of blood vessel patterns also called as vein patterns. A multimodal identification system has been proposed in this paper which uses Contourlet transform to analyze the features present in palm print and palm vein images. The proposed algorithm captures local minutae and a global feature from a palm print and palm vein images and stores them as a compact code. After extraction of the ROI from the source images the (2-D) image spectrum is divided into fine sub-components (called subbands) using iterated directional filter bank structure. The feature matching technique is then performed using Euclidean Distance algorithm. For this algorithm CASIA Palm print Database V1.0 is used.