Biometric science is one of the important applications in the pattern recognition field. There are several modalities used in the biometric applications, among these different traits we choose the iris modality. Therefore, this paper proposes a multi-biometric technique which combines the both units of the iris modality: the left and the right irises. The fusion combines the advantages of the two instances. For the both units of the iris, the segmentation is realized by a modified method and the feature extraction is done by a global approach (the Daubechies wavelets). The Support Vector Machine SVM is used to obtain scores for fusion. Then the scores obtained are normalized by Min-Max method and the fusion is performed at score level by the combination of two methods: a combination method with a classification method. The Fusion is tested using four databases which are: CASIAV4 database, SDUMLA-HMT database, MMU1, and MMU2 databases. The obtained results have confirmed that the multi-biometric systems are better than the mono-modal systems according to their performance.

The biometric authentication, which use the characteristic of persons to verify their identity by using their behavioral and physiological characteristics are an important application of the pattern recognition. There are different biometric modalities used to achieve the task of recognition. Among the most popular traits biometric currently used in several applications are the face and the iris. This paper proposes a multi-biometric technique which combines the face modality with the both irises (the left and the right irises) to authenticate the persons. The fusion of these two traits biometrics combines the advantages of the both instances of the iris modality with the face modality. The wavelets are used for the extraction of the biometrics features and the Support Vector Machine is used to obtain scores for fusion. Then, the Min-Max operator is used to normalize these scores. The fusion is operated at score level by the combination of two methods: a combination method and a classification method. So, we used the five rules (Sum, Product, Max, Min, Mean) combined with a classification method for the fusion. The Fusion is tested using the SDUMLA-HMT database. The experimental results show that multi-biometric systems achieve the task of recognition better than the mono-modal systems.