Multimodal recognition fusing ear and profile face based on KPCA

Ear recognition has been proved to be a promising subject in biometrics authentication. The fusion of ear and face biometrics could fully utilize their connection relationship, and possess the merit of recognizing persons without their cooperation because of earpsilas special physiological structure and location. In this paper a feature fusion method based on KPCA is proposed and applied to multimodal recognition fusing ear and profile face. With the method, the associated feature vectors of ear and profile face are established for the following classification. The experimental results show that the method is efficient for feature fusion, and the multimodal recognition based on ear and profile face performs better than ear or profile face unimodal biometric recognition.