A multimodal iris recognition using Gabor transform and Contourlet

Abstract

Multimodal biometric systems use two or more biometric modalities in a verification process. The main reason to combine different modalities is related to improve the recognition accuracy. This paper deals with various possible scenarios in a multimodal biometric system using two iris recognitions and also the levels of fusion and the integration strategies to improve overall system accuracy. With this in mind, first, we implement the Daugman's iris system using the Gabor transform and Hamming distance. Second, we propose an iris feature extraction method having a property of size invariant through the fuzzy-LDA with five types of Contourlet transform. Finally, we establish a multi-modal biometric system based on two iris recognition systems. To effectively aggregate two systems, we use statistical distribution models based on matching values for genuine and impostor, respectively. And then, we perform to make comparisons of performance of the fusion algorithms such as weighted summation, support vector machine, fisher discriminant analysis, and Bayesian classifier.