Finger knuckle print recognition system using compound local binary pattern

With the explosive growth of digital transactions, the security of personal identity presents a serious challenge in our world today. It has become necessary to provide reliable and robust recognition systems. To overcome this problem, we propose a novel approach for finger knuckle print using Compound Local Binary Pattern (CLBP). Unlike the LBP operator, the CLBP add an extra bit for each P bits encoded by LBP corresponding to a neighbor of the local neighborhood, in order to construct a robustious feature descriptor that exploits both the sign and the inclination information of the differences between the center and the neighbor gray values. The effectiveness of proposed method has been verified on PolyU FKP database. The experimental results show that the recognition rates are significantly improved compared with others methods existing in literature. The recognition rate of the proposed method is the highest among the other algorithms. The optimal recognition rates obtained is 98,18%, 99,29%, 98,48% and 98,89% for Left Index, Left Middle, Right Index and Right Middle, respectively.