Application of Masking and Ellipse Fitting in Pupil Localization

The human eyes feature plays an important role in the human face feature extraction and the human face recognition. It can be used to correct the human face posture and locate the other face key features by the coordinates of the eyes on the human face. In this paper, we train the human eyes detection cascade strong classifier which be used to detect the human eyes position on the human face , and then locate the pupil center position by making use of the ellipse fitting algorithm and the human eyes mask templates. The experimental results show that these algorithms which be used in this paper can accurately locate the pupil center position.

[1]  Alan L. Yuille,et al.  Feature extraction from faces using deformable templates , 2004, International Journal of Computer Vision.

[2]  Yoshinobu Ebisawa,et al.  Effectiveness of pupil area detection technique using two light sources and image difference method , 1993, Proceedings of the 15th Annual International Conference of the IEEE Engineering in Medicine and Biology Societ.

[3]  Hanqi Zhuang,et al.  On improving eye feature extraction using deformable templates , 1994, Pattern Recognit..

[4]  Yoshinobu Ebisawa.  Improved video-based eye-gaze detection method , 1998, IEEE Trans. Instrum. Meas..

[5]  Hong Yan,et al.  Locating and extracting the eye in human face images , 1996, Pattern Recognit..

[6]  Robert Mariani,et al.  Face detection and precise eyes location , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[7]  Pong C. Yuen,et al.  Variance projection function and its application to eye detection for human face recognition , 1998, Pattern Recognit. Lett..

[8]  Alex Pentland,et al.  View-based and modular eigenspaces for face recognition , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.