Multimodal biometric fusion at feature level: Face and palmprint

Multimodal biometrics has recently attracted substantial interest for its high performance in biometric recognition system. In this paper we introduce multimodal biometrics for face and palmprint images using fusion techniques at the feature level. Gabor based image processing is utilized to extract discriminant features, while principal component analysis (PCA) and linear discriminant analysis (LDA) are used to reduce the dimension of each modality. The output features of LDA are serially combined and classified by a Euclidean distance classifier. The experimental results based on ORL face and Poly-U palmprint databases proved that this fusion technique is able to increase biometric recognition rates compared to that produced by single modal biometrics.