A robust system of face detection and precise face organ location

Human face detection and face organ feature location are both important steps in automatic visual interpretation and human face recognition systems. In this paper, a robust system which focuses on human face detection and face organ location is introduced. We improve the cascade-structured classifier of the human face detector, and integrate human face super-resolution algorithm into our system to help processing low-resolution faces. Template matching, feature space analysis method (PCA) combined with AdaBoost algorithm are used to get the precise location of eye feature, and the locations of other face organs are incorporated in the similar framework. The experimental results demonstrate that the proposed system has good performance on actual images.