Comparing Feature and Matching Score Fusion Levels of Multimodal Biometrics Recognition System using Particle Swarm Optimization

摘要

Multimodal biometric systems which fuse information from a number of biometrics are most spreads lately because they are able to overcome problems in unimodal biometric systems. Most of the proposed multibiometric systems offer one level of fusion. In this paper, a comparison between two levels of fusion has been proposed; a proposed fusion system of three biometrics at the feature level based on Particle Swarm Optimization approach (PSO) is presented with a new multi objective fitness function for PSO has been used. Also the score level fusion rule is optimized using (PSO) Particle Swarm Optimization. Results shown that matching score fusion outperforms matching score fusion in one multimodal system (palmprint_Knuckle), while matching score fusion outperforms feature fusion in the other two systems.