Eye Detection and Tracking

We propose a probabilistic framework to learn the good features and localize eye and
pupil from face region.


1. Peng Wang and Qiang Ji, "Learning Discriminant Features for Multi-View Face and Eye Detection", 

 IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), San Diego, CA, June 2005

2. Peng Wang, Matthew B. Green, Qiang Ji and James Wayman, "Automatic Eye Detection and 

Its Validation" , IEEE Workshop on Face Recognition Grand Challenge Experiments (with CVPR), San Diego, CA, June 2005

4. Peng Wang and Qiang Ji, Multi-View Face and Eye Detection Using Discriminant Features, Computer Vision and Image Understanding, Vol. 105, Issue 2, February 2007

3. CVIU Special Issue on Eye Detection and Tracking

1.Eye detection in images
(Test on FERET, FRGC database, also thank MPLAB@UCSD for providing some test images )
2. Face and eye detection in video
The eyes are detected after the face region is identified.
Real time face and eye detection demo
3. Blink detection in video
After face and eyes are detected, we apply the same method to detect eye blink.
Demo: Blink detection in video.