Score Fusing In a Multimodal System

Biometrics consists of techniques for identifying persons based upon one or more intrinsic physical or behavioral traits. A system which is based only on a single biometric identifier in making a personal identification is often not able to meet the desired performance requirements. Multimodal biometrics is an emerging field of biometric technology, where more than one biometric trait to improve the combined performance. This paper presents a new approach to combine decisions from face and fingerprint classifiers for multi-modal biometry by exploiting the individual classifier space on the basis of availability of class specific information present in the classifier space. This system takes advantage of the capabilities of each individual biometrics. It can be used to overcome some of the limitations of a single biometrics, increases the performance and robustness of identity authentication systems. In this context, a key matter is the fusion of a two different modality to obtain a final decision of classification. We propose to evaluate a binary classification schemes: support vector Machine to carry on the fusion. The experimental results show that merging multiple biometrics can help to reduce the error rate of the system.