Abstract
A closed-loop algorithm to detect human face using color information and reinforcement learning is presented in this paper. By using a skin-color selector, the regions with color “like” that of human skin are selected as candidates for human face. In the next stage, the candidates are matched with a face model and given an evaluation of the match degree by the matching module. And if the evaluation of the match result is too low, a reinforcement learning stage will start to search the best parameters of the skin-color selector. It has been tested using many photos of various ethnic groups under various lighting conditions, such as different light source, high light and shadow. And the experiment result proved that this algorithm is robust to the varying lighting conditions and personal conditions.
References
Birchfield, S., 1998. Elliptical Head Tracking Using Intensity Gradients and Color Histograms. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, CA, p. 232–237.
Bulurswar, S. D., Darper, B. A., 1994. Non-parametric classification of pixels under varying outdoor illumination. Proceedings of the ARPA Image Understanding Workshop, Monterey, CA, p. 1619–1626.
Huang, C. L., Chen, C. W., 1992. Human facial feature extraction for face interpretation and recognition.Pattern Recognition 25(12), 1435–1444.
Lee, C. H., Kim, J. S., Park, K. H., 1996. Automatic human face location in a complex background using motion and color information.Pattern Recognition,29(11): 1305–1320.
Miao, J., Yin, B. C., 1999. A hierarchical multiscale and multiangle system for human face detection in complex background using gravity-center template.Pattern Recognition,32(10): 1237–1248.
Peng, J., Bhanu Bir, 1998. Closed loop object recognition using reinforcement learning.IEEE. Trans. on Pattern Analysis & Machine Intelligence,20(2): 139–154.
Rowley, H. A., Baluja Shumeet, 1998. Neural network-based face detection.IEEE Trans. on Pattern Analysis & Machine Intelligence,20(1): 23–38.
Saber, E., Tekalp, A. M., 1998. Frontal-view face detection and facial feature extraction using color, shape and symmetry based cost functions.Pattern Recognition Letters,19: 669–680.
Sung, K. K., Poggio, T., 1998. Example-based learning for view-based human face detection.IEEE Trans. on Pattern Analysis & Machine Intelligence,20(1): 39–50.
Turk, M. A., Pentland, A. P., 1996. Face recognition using eigenfaces. Proceedings of Intermation Conference on Pattern Recognition, p. 586–591.
Wu, H., Yokoyama, T., Pramadihanto, D., et al., 1996. Face and facial feature extraction from color image, International Conference on Pattern Recognition' 96, p. 345–350.
Wu, H. Y., Chen, Q., Masahiko, Y., 1999. Face detection from color images using a fuzzy pattern matching method.IEEE Trans. on Pattern Analysis & Machine Intelligence,21(6): 557–563.
Wang, H. Y., Li, H. D., Ye, X. Q., 2000. Training a neural network for moment based image edge detection.Journal of Zhejiang University SCIENCE,1(4): 398–401.
Yang, G. Z., Huang, T. S., 1994. Human face detection in a complex background.Pattern Recognition,27(1): 43–63.
Yang, X. L., 1996. The Neural Mechanical System of Vision. Shanghai Science and Technology Press (in Chinese).
Yuille, A., Hallinan, P., Cohen, D., 1996. Feature extraction from faces using deformable templates.International Journal of Computer Vision,8(2): 1992.
Zhong, J. T., 2000. Human Facial Feature Detection. M. S. Thesis, Zhejiang University (in Chinese).
Author information
Authors and Affiliations
Additional information
Project supported by the National Natural Science Foundation of China (No. 60105003) and Zhejiang Provincial Natural Science Foundation of China (No. 600025).
Rights and permissions
About this article
Cite this article
Dong-hui, W., Xiu-qing, Y. & Wei-kang, G. A closed-loop algorithm to detect human face using color and reinforcement learning. J. Zheijang Univ.-Sci. 3, 72–76 (2002). https://doi.org/10.1631/BF02881846
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1631/BF02881846