Multimodal biometric: Iris and face recognition based on feature selection of iris with GA and scores level fusion with SVM

The purpose of this work is to develop a biometric bimodal system for the verification of the person: Our bimodal system is going to combine the modality of the face with that of the iris. Firstly, the modality of the face constitutes one of the most natural ways to recognize a person. On the other hand, the modality of the iris is certainly one of the most used. We introduce the recognition of the face by using a Discrete Cosine Transform DCT, it transforms an image signal from a space representation into a Frequency domain, and PCA transform, which treat the face image as a stochastic variable. The performance of the systems of recognition of the iris are significantly improved by the precision of the segmentation with Snake method. The fusion in feature level of two features extractors, called Gabor filter and Zernike moment through the feature selection using a Genetic Algorithm in order to combine the properties of global and local methods. Later we will study a fusion at the scores level of the face and iris modalities after being normalized by using SVM classification method. The performance of our system is tested using CASIA-IrisV3-Interval data base, the recognition rate achieved with this data base is 98.8.