Eye localization is an important part in face recognition system, because its precision closely affects the performance of face recognition. Although various methods have already achieved high precision on the face images with high quality, their precision will drop on low quality images. In this paper, we propose a robust eye localization method for low quality face images to improve the eye detection rate and localization precision. First, we propose a probabilistic cascade (P-Cascade)

more »

... rk, in which we reformulate the traditional cascade classifier in a probabilistic way. The P-Cascade can give chance to each image patch contributing to the final result, regardless the patch is accepted or rejected by the cascade. Second, we propose two extensions to further improve the robustness and precision in the P-Cascade framework. There are: (1) extending feature set, and (2) stacking two classifiers in multiple scales. Extensive experiments on JAFFE, BioID, LFW and a self-collected video surveillance database show that our method is comparable to state-of-the-art methods on high quality images and can work well on low quality images. This work supplies a solid base for face recognition applications under unconstrained or surveillance environments. * Stan Z. Li is the corresponding author. True alignment Mis-alignment Recently, the leading methods in eye localization are almost based on Boosting classification, regression, Boost-ing+Cascade, Boosting+SVM, and other variants. Considering precision and computation complexity, we propose a new method for low quality images based on LBP+Boosting+Cascade [1, 23] . For two-class problem, Boosting can select the most effective subset from an overcomplete feature set. Also cascade can reject irrelevant