New algorithm for eyes detection in images
一种新的图像中的人眼检测算法*

This paper proposed a new algorithm for eyes detection in the images. First, in a known face image, the homomorphic filter was used to enhance the contrast of the image and the iterative thresh choosing algorithm changed the gray images into binary ones. According to certain priori knowledge, it could get the candidate field of the eyes. Then this paper proposed a user-defined template based on the minimum enclosing rectangle (MER) to complete the finally orientation, and found the center of the eyes using the area centroid. According to many tests, the algorithm can easily and quickly detect the eyes.