Locating human eyes in face images based on illumination normalization and progressive thresholding

Based on illumination normalization and progressive thresholding, this paper presents a novel algorithm for automatic localization of human eyes in still images with complex background. First of all, Retinex method is used to realize normalizing of the face image. Secondly, a determination criterion of eye location is established by the priori knowledge of geometrical facial features. Thirdly, a range of threshold values that would separate eye blocks from others in a segmented face image is estimated. With the progressive increase of the threshold by an appropriate step in that range, once two eye blocks appear from the segmented image, they will be detected by the determination criterion of eye location. Finally, the 2-D correlation coefficient is used as a symmetry similarity measure to check the factuality of the two detected eyes. The experimental results demonstrate the high efficiency of the algorithm in runtime and correct localization rate.