图像中人脸和眼睛的定位及其分割方法的研究

The Study of Method for Faces Detection and Segmentation

提出了一种新的在复杂背景下对未知大小、位置和数目的人脸进行定位和分割的算法．它利用基于知识的金字塔方法，主要由３部分组成：较高的２级是在多尺度屋顶边缘检测的基础上，先利用Ｂ－样条二进小波变换来检测在不同分辨率下的极小值点（对应眼睛）和极大值点（对应人脸）；再利用尺度、包含和对称等关系进行初步筛选；最后利用人眼的特征确定眼睛的位置．因此，这种方法能够在复杂背景的灰度图像中检测不同尺度下的未知人脸，并进行初步的分割．最后，给出了一些实验结果．

A new method to locate and segment human faces in a complex background is proposed. This system utilizes a hierarchical knowledge based method and consists of three levels. The higher two levels are based on detecting maximum(corresponding to faces) and minimum(corresponding to eyes) in multiresolution image using B spline dyadic wavelet transform, and then initial selection is made using some knowledge, e.g. the relation of scale between eyes and face,symmetry of face, etc. The last level will make the face and eyes certainly according to the features of face. This method can locate and segment unknown human faces spanning a wide range of sizes in an intensity image. Some experimental results are presented.