Finding human faces in a picture
We present a multiscale ruled-based algorithm for detecting human faces in still monochromatic images with complex background. To reduce search time, three coarse-to-fine levels are used. At each level, face candidates are picked or rejected according to a small set of rules which are hand-crafted from training samples. Preliminary results are encouraging and indicate that our algorithm compares favorably with existing methods.
Unable to display preview. Download preview PDF.
- 1.M. Turk and A. Pentland, Face recognition using eigenfaces, Proc. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 586–591, June 1991.Google Scholar
- 2.M. Kosygi, Human face identification using mosaic pattern and BPN, ACNN'91, 1991.Google Scholar
- 3.M. Clark, Face recognition using a connectionist model, David Sarnoff Research Center and the University of Pennsylvania, pp. 1–12, May 1989.Google Scholar
- 4.V. Govindaraju, S. N. Srihari and D. Sher, A computational model for face location based on cognitive principles, Proceedings of AAAI'92, San Jose, CA, 1992.Google Scholar
- 5.T. Agui, Y. Kokubo, H. Nagahashi, and T. Nagao, Extraction of face regions from monochromatic photographs using neural networks, Proceedings of International Conference on Robotics, Singapore, 1992.Google Scholar