从边缘图象计算本征脸以进行基于Hausdorff距离的人脸识别

he different face regions have different degrees of importance for face recognition. In previous Hausdorff distance measures for face recognition, such as Spatially Eigen-Weighted Hausdorff distance (SEWHD), the weighting function is computed from grayscale images. However, Hausdorff distance is a measure for two binary point sets, not for grayscale point sets. A point which is important in grayscale domain does not necessarily mean it is important in edge domain. In this paper, a new weighting function of Hausdorff distance measure is proposed for face recognition. The weighting function is based on the eigenface of face edge images, not the eigenface of grayscale images in previous method. When comparing the edge images of the face model and that of a test face edge image in face recognition, the weighted Hausdorff distance can reflect the discriminative properties of face edge images effectively. Experimental results show the new method achieves higher recognition rate comparing with previous Hausdorff distance measures