Appearance based face identification and classification. A Combining approach

We propose in this paper a search approach which aim to improve identification in biometric databases. We work with face images and we develop appearance-based Eigenfaces method to generate holistic and discriminant features. These feature vectors, which describe faces, are often used to establish the required identity in a recognition process. In this work, we introduce a clustering process which aims to split biometric databases into partitions and to simplify consequently recognition task within these databases. Various studies were undertaken on search strategies to adjust feature extraction and clustering parameters. We simulate four experts which learn differently and acquire various knowledge to recognize facial images. In addition, we evaluate the robustness and the performance of our approach against noise effect through different test series. We propose, finally, to combine and to fuse clustering classifiers and identification processes what improve and simplify our recognition system task.