2018-11-16 Welcome guest,  Sign In  |  Sign Up
Chin. Opt. Lett.
 Home  List of Issues    Issue 11 , Vol. 01 , 2003    A novel algorithm for automatic localization of human eyes


A novel algorithm for automatic localization of human eyes
Liang Tao1;2, Juanjuan Gu3, Zhenquan Zhuang2
1Department of Electronic Engineering and Information Science, Anhui University, Hefei 2300392Department of Electronic Science and Technology, University of Science and Technology of China, Hefei 2300263Department of Computer and Information Engineering, Hefei Association University, Hefei 230022

Chin. Opt. Lett., 2003, 01(11): pp.641-641-

DOI:
Topic:Image processing
Keywords(OCIS Code): 100.5010  330.1880  100.2000  

Abstract
Based on geometrical facial features and image segmentation, we present a novel algorithm for automatic localization of human eyes in grayscale or color still images with complex background. Firstly, a determination criterion of eye location is established by the prior knowledge of geometrical facial features. Secondly, a range of threshold values that would separate eye blocks from others in a segmented face image (i.e., a binary image) are estimated. Thirdly, with the progressive increase of the threshold by an appropriate step in that range, once two eye blocks appear from the segmented image, they will be detected by the determination criterion of eye location. Finally, the 2D correlation coefficient is used as a symmetry similarity measure to check the factuality of the two detected eyes. To avoid the background interference, skin color segmentation can be applied in order to enhance the accuracy of eye detection. The experimental results demonstrate the high efficiency of the algorithm and correct localization rate.

Copyright: © 2003-2012 . This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

 View PDF (659 KB)

Share:


Received:2003/7/22
Accepted:
Posted online:

Get Citation: Liang Tao, Juanjuan Gu, Zhenquan Zhuang, "A novel algorithm for automatic localization of human eyes," Chin. Opt. Lett. 01(11), 641-641-(2003)

Note: This research was supported by the Excellent Young Teachers Program of the Ministry of Education, P. R. China, the National Natural Science Foundation of China (No. 60375010), and the Excellent College Teachers Program of the Education Committee in Anhui Province. L. Tao’s e-mail address is taoliang@ustc.edu.



References

1. A. Samal and P. A. Iyengar, Pattern Recognition 25, 65 (1992).

2. R. Chellappa, C. L. Wilson, and S. Sirohey, Proceedings of IEEE 83, 705 (1995).

3. S. G. Shan, W. Gao, and X. L. Chen, J. Software (in Chinese) 12, 570 (2001).

4. A. L. Yuille, D. Cohen, and P. Hallinan, in Proceedings of IEEE CVPR’89 104 (1989).

5. X. Xie, R. Sudhakar, and H. Zhuang, Pattern Recognition 27, 791 (1994).

6. E. Hjelm°as, Computer Vision and Image Understanding 83, 236 (2001).

7. Y. J. Zhang, Image Segmentation (in Chinese) (Science in China Press, Beijing, 2001).

8. L. Tao, J. J. Gu, Q. W. Gao, and Z. Q. Zhuang, Proc. SPIE 4875, 710 (2002).


Save this article's abstract as
Copyright©2018 Chinese Optics Letters 沪ICP备15018463号-7 公安备案沪公网安备 31011402005522号