This work presents a new method of projection peak analysis for rapid eye localization. First, the eye region is segmented from the face image by setting appropriate candidate window. Then, a threshold is obtained by histogram analysis of the eye region image to binarize and segment the eyes out of the eye region. Thus, a series of projection peak will be derived from vertical and horizontal gray projection curves on the binary image, which is used to confirm the positions of the eyes. The proposed eye-localization method does not need any a priori knowledge and training process. Experiments on three face databases show that this method is effective, accurate and rapid in eye localization, which is fit for real-time face recognition system.

Some result images (from top to bottom): some frontal samples in FERET; Some samples with glasses in FERET; some profile samples in FERET; some frontal samples in BioID; some samples with glasses in BioID; some samples from JAFFE; some samples that eyes are wrongly located.

[1] J. Dai, D. Liu and J. Su. The Method of Rapid Eye Localization Based on Projection Peak. Pattern Recognition and Artificial Intelligence (PRAI) (in Chinese, Indexed by EI), 22(4):605-609, 2009.
[2] J. Dai, D. Liu and J. Su. Projection Peak Analysis for Rapid Eye Localization. In Proc. of The International Conference on Computer Vision Theory and Applications, pages 315-320, 2009.