Anti-Faces for Detection
This paper offers a novel detection method, which works well even in the case of a complicated image collection - for instance, a frontal face under a large class of linear transformations. It was also successfully applied to detect 3D objects under different views. Call the class of images, which should be detected, a multi-template.
The detection problem is solved by sequentially applying very simple filters (or detectors), which are designed to yield small results on the multi-template (hence “anti-faces”), and large results on “random” natural images. This is achieved by making use of a simple probabilistic assumption on the distribution of natural images, which is borne out well in practice, and by using a simple implicit representation of the multi-template.
Only images which passed the threshold test imposed by the first detector are examined by the second detector, etc. The detectors have the added bonus that they act independently, so that their false alarms are uncorrelated; this results in a percentage of false alarms which exponentially decreases in the number of detectors. This, in turn, leads to a very fast detection algorithm, usually requiring (1 +δ)N operations to classify an N-pixel image, where δ < 0:5. Also, the algorithm requires no training loop.
The suggested algorithm’s performance favorably compares to the well-known eigenface and support vector machine based algorithms, and it is substantially faster.
KeywordsSupport Vector Machine False Alarm Input Image False Alarm Rate Machine Intelligence
- 3.S. Geman and D. Geman. Stochastic relaxation, Gibbs distribution, and the Bayesian restoration of images. IEEE Trans. on Pattern Analysis and Machine Intelligence, 6:721–741, June 1984.Google Scholar
- 4.D. Keren and M. Werman. Probabilistic analysis of regularization. IEEE Trans. on Pattern Analysis and Machine Intelligence, 15:982–995, October 1993.Google Scholar
- 5.Y. Lamdan and H.J. Wolfson. Geometric hashing: A general and efficient model-based recognition scheme. In Proc. Int’l. Conf. Comp. Vision, pages 238–249, 1988.Google Scholar
- 9.E. Osuna, R. Freund, and F. Girosi. Training support vector machines: An application to face detection. In IEEE Conference on Computer Vision and Pattern Recognition, 1997.Google Scholar
- 10.C. P. Papageorgiou, M. Oren, and T. Poggio. A general framework for object detection. In International Conference on Computer Vision, pages 555–562, 1998.Google Scholar
- 13.D. Roobaert and M.M. Van Hulle. View-based 3d object recognition with support vector machines. In IEEE International Workshop on Neural Networks for Signal Processing, pages 77–84, USA, 1999.Google Scholar
- 15.H. A. Rowley, S. Baluja, and T. Kanade. Rotation invariant neural network-based face detection. In IEEE Conference on Computer Vision and Pattern Recognition, 1998.Google Scholar
- 19.D. Terzopoulos. Regularization of visual problems involving discontinuities. IEEE Trans. on Pattern Analysis and Machine Intelligence, 8:413–424, August 1986.Google Scholar
- 21.M. Turk and A. Pentland. Face recognition using eigenfaces. In Proceedings of the Int’l Conf. on Computer Vision and Pattern Recognition, pages 586–591, 1991.Google Scholar
- 22.Matthew Turk. Personal communication, December 1999.Google Scholar
- 25.I. Weiss. Geometric invariants and object recognition. International Journal of Computer Vision, 10:3:201–231, June 1993.Google Scholar