Multiresolution eye location from image

This paper presents a new method for locating eye. In the first stage, the coarse face region is found from original image using generation method. In the second stage, the proposed method finds the coarse eye region from multiresolution subimage using wavelet transformation based on the edge distribution information in the different scale image. In the third stage, the eyes special site in the face image can be obtained. The experimental results have shown that the proposed method can locate eyes accurately from the input image with complex background. At the same time, this proposed method is needed not to create the particular wavelet function.