PCA based Multimodal Biometrics using Ear and Face Modalities

Automatic person identification is an important task in computer vision and related applications. Multimodal biometrics involves more than two modalities. The proposed work is an implementation of person identification fusing face and ear biometric modalities. We have used PCA based neural network classifier for feature extraction from the images. These features are fused and used for identification. PCA method was found better if the modalities were combined. Identification was made using Eigen faces, Eigen ears and their features. These were tested over own created database.