Partially Occluded Object Recognition Using Statistical Models
International Journal of Computer Vision
Hi-index | 0.00 |
In this paper, a novel method for face detection is presented, which is robust to face, illumination, and pose variations. This method is based on processing of image features constructed using multi-resolution techniques, and using statistical models of these multi-resolution features to detect the presence of faces in an image. Simulation results show that the new method significantly outperforms traditional methods based on normalized correlation of images with an average face.