An Eye Detection Algorithm Using Pixel to Edge Information

We present a new method for eyes localization on a face, based only on geometrical information. A face detector is applied first to detect the bounding box of the face, and the edge map is extracted. A vector is assigned to every pixel, pointing to the closest edge pixel. Length and slope information for these vectors is consequently used to detect and localize the eyes. The method has been tested on two face databases with very good results.

[1]  J. Canny.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  William Rucklidge,et al.  Efficient Visual Recognition Using the Hausdorff Distance , 1996, Lecture Notes in Computer Science.

[3]  Jiri Matas,et al.  XM2VTSDB: The Extended M2VTS Database , 1999 .

[4]  Klaus J. Kirchberg,et al.  Robust Face Detection Using the Hausdorff Distance , 2001, AVBPA.

[5]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[6]  Rainer Lienhart,et al.  An extended set of Haar-like features for rapid object detection , 2002, Proceedings. International Conference on Image Processing.

[7]  Jianxin Wu,et al.  Efficient face candidates selector for face detection , 2003, Pattern Recognit..

[8]  Zhi-Hua Zhou,et al.  Projection functions for eye detection , 2004, Pattern Recognit..

[9]  Paul A. Viola,et al.  Robust Real-Time Face Detection , 2001, International Journal of Computer Vision.

[10]  Timothy F. Cootes,et al.  A Multi-Stage Approach to Facial Feature Detection , 2004, BMVC.