Palmprint and Face Based Multimodal Recognition Using Pso Dependent Feature Level Fusion

Biometrics refers to a scientific discipline which involves automatic methods for recognizing people based on their physiological or behavioural characteristics. Biometric systems that use a single trait are called unimodal systems, whereas those that integrate two or more traits are referred to as multimodal biometric systems. A multimodal biometric system requires an integration scheme to fuse the information obtained from the individual modalities. In this paper, we have designed and developed a technique for multi-modal biometric recognition using feature level fusion. Initially we consider two data sets namely face and palmprint. Using multi texton histogram we extract the features from the face and palmprints directly. We concatenate the face and palmprint using XOR, AND and OR gate with the help of Particle Swarm Optimization (PSO) algorithm. In recognition, the concatenated feature is matched through distance matching and distance score provides recognition identity of a person. The proposed technique is implemented with the help of evaluation metrics such as false acceptance rate, false rejection rate and accuracy. Finally the comparative analysis for the proposed fusion technique results 40% better accuracy, when compared with the existing techniques.