The Community for Technology Leaders
RSS Icon
Subscribe
Issue No.03 - March (2008 vol.30)
pp: 369-382
ABSTRACT
A cascade face detector uses a sequence of node classifiers to distinguish faces from non-faces. This paper presents a new approach to design node classifiers in the cascade detector. Previous methods used machine learning algorithms that simultaneously select features and form ensemble classifiers. We argue that if these two parts are decoupled, we have the freedom to design a classifier that explicitly addresses the difficulties caused by the asymmetric learning goal. There are three contributions in this paper. The first is a categorization of asymmetries in the learning goal, and why they make face detection hard. The second is the Forward Feature Selection (FFS) algorithm and a fast pre- omputing strategy for AdaBoost. FFS and the fast AdaBoost can reduce the training time by approximately 100 and 50 times, in comparison to a naive implementation of the AdaBoost feature selection method. The last contribution is Linear Asymmetric Classifier (LAC), a classifier that explicitly handles the asymmetric learning goal as a well-defined constrained optimization problem. We demonstrated experimentally that LAC results in improved ensemble classifier performance.
INDEX TERMS
face detection, cascade classifier, asymmetry, feature selection
CITATION
Jianxin Wu, S. Charles Brubaker, Matthew D. Mullin, James M. Rehg, "Fast Asymmetric Learning for Cascade Face Detection", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.30, no. 3, pp. 369-382, March 2008, doi:10.1109/TPAMI.2007.1181
REFERENCES
[1] K. Sung and T. Poggio, “Example-Based Learning for View-Based Human Face Detection,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 20, no. 1, pp. 39-51, Jan. 1998.
[2] H.A. Rowley, S. Baluja, and T. Kanade, “Neural Network-Based Face Detection,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 20, no. 1, pp. 23-38, Jan. 1998.
[3] H. Schneiderman and T. Kanade, “A Statistical Model for 3D Object Detection Applied to Faces and Cars,” Proc. Int'l Conf. Computer Vision and Pattern Recognition, pp. 746-751, 2000.
[4] M.-H. Yang, D. Roth, and N. Ahuja, A SNoW-Based Face Detector, Advances in Neural Information Processing Systems 12, pp. 862-868, 2000.
[5] E. Osuna, R. Freund, and F. Girosi, “Training Support Vector Machines: An Application to Face Detection,” Proc. Int'l Conf. Computer Vision and Pattern Recognition, pp. 130-136, 1997.
[6] F. Fleuret and D. Geman, “Coarse-to-Fine Face Detection,” Int'l J.Computer Vision, vol. 41, no. 1-2, pp. 85-107, 2001.
[7] P. Viola and M. Jones, “Robust Real-Time Face Detection,” Int'l J.Computer Vision, vol. 57, no. 2, pp. 137-154, 2004.
[8] Y. Amit and D. Geman, “A Computational Model for Visual Selection,” Neural Computation, vol. 11, no. 7, pp. 1691-1715, 1999.
[9] R. Osadchy, M. Miller, and Y. LeCun, “Synergistic Face Detection and Pose Estimation with Energy-Based Model,” Advances in Neural Information Processing Systems 17, pp. 1017-1024, 2005.
[10] R.E. Schapire, Y. Freund, P. Bartlett, and W.S. Lee, “Boosting the Margin: A New Explanation for the Effectiveness of Voting Methods,” The Annals of Statistics, vol. 26, no. 5, pp. 1651-1686, 1998.
[11] J. Wu, J. Rehg, and M. Mullin, “Learning a Rare Event Detection Cascade by Direct Feature Selection,” Advances in Neural Information Processing Systems 16, pp. 1523-1530, 2004.
[12] J. Wu, M. Mullin, and J. Rehg, “Linear Asymmetric Classifier for Cascade Detectors,” Proc. 22nd Int'l Conf. Machine Learning, pp.993-1000, 2005.
[13] G.M. Weiss, “Mining with Rarity: A Unifying Framework,” ACM SIGKDD Explorations Newsletter, vol. 6, no. 1, pp. 7-19, 2004.
[14] P. Viola and M. Jones, “Fast and Robust Classification Using Asymmetric AdaBoost and a Detector Cascade,” Advances in Neural Information Processing Systems 14, pp. 1311-1318, 2002.
[15] M.-H. Yang, D.J. Kriegman, and N. Ahujua, “Detecting Faces in Images: A Survey,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 24, no. 1, pp. 34-58, Jan. 2002.
[16] M. Elad, Y. Hel-Or, and R. Keshet, “Pattern Detection Using a Maximal Rejection Classifier,” Pattern Recognition Letters, vol. 23, no. 12, pp. 1459-1471, 2002.
[17] D. Keren, M. Osadchy, and C. Gotsman, “Antifaces: A Novel, Fast Method for Image Detection,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 23, no. 7, pp. 747-761, July 2001.
[18] S. Romdhani, P. Torr, B. Schoelkopf, and A. Blake, “Computationally Efficient Face Detection,” Proc. Int'l Conf. Computer Vision, pp. 695-700, 2001.
[19] B. Heisele, T. Serre, S. Mukherjee, and T. Poggio, “Feature Reduction and Hierarchy of Classifiers for Fast Object Detection in Video Images,” Proc. Int'l Conf. Computer Vision and Pattern Recognition, pp. II:18-24, 2001.
[20] S. Baker and S. Nayar, “Pattern Rejection,” Proc. Int'l Conf. Computer Vision and Pattern Recognition, pp. 544-549, 1996.
[21] C. Papageorgiou, M. Oren, and T. Poggio, “A General Framework for Object Detection,” Proc. Int'l Conf. Computer Vision, pp. 555-562, 1998.
[22] H. Sahbi and D. Geman, “A Hierarchy of Support Vector Machines for Pattern Detection,” J. Artificial Intelligence Research, vol. 7, pp. 2087-2123, 2006.
[23] R.E. Schapire, Y. Singer, and A. Singhal, “Boosting and Rocchio Applied to Text Filtering,” Proc. Int'l Conf. Research and Development in Information Retrieval, pp. 215-223, 1998.
[24] G.J. Karakoulas and J. Shawe-Taylor, “Optimizing Classifiers for Imbalanced Training Sets,” Advances in Neural Information Processing Systems 11, pp. 253-259, 1999.
[25] W. Fan, S.J. Stolfo, J. Zhang, and P.K. Chan, “Adacost: Misclassification Cost-Sensitive Boosting,” Proc. 16th Int'l Conf. Machine Learning, pp. 97-105, 1999.
[26] K.M. Ting, “A Comparative Study of Cost-Sensitive Boosting Algorithms,” Proc. 17th Int'l Conf. Machine Learning, pp. 983-990, 2000.
[27] K. Huang, H. Yang, I. King, M. Lyu, and L. Chan, “The Minimum Error Minimax Probability Machine,” J. Machine Learning Research, vol. 5, pp. 1253-1286, 2004.
[28] G. Blanchard and D. Geman, “Sequential Testing Designs for Pattern Recognition,” Annals of Statistics, vol. 33, no. 3, pp. 1155-1202, 2005.
[29] R.L. Rivest, “Learning Decision Lists,” Machine Learning, vol. 2, no. 3, pp. 229-246, 1987.
[30] M. Anthony, “Generalization Error Bounds for Threshold Decision Lists,” J. Machine Learning Research, vol. 5, pp. 189-217, 2004.
[31] R. Lienhart, A. Kuranov, and V. Pisarevsky, “Empirical Analysis of Detection Cascades of Boosted Classifiers for Rapid Object Detection,” Lecture Notes in Computer Science, vol. 2781, pp. 297-304, 2003.
[32] K. Levi and Y. Weiss, “Learning Object Detection from a Small Number of Examples: The Importance of Good Features,” Proc. Int'l Conf. Computer Vision and Pattern Recognition, pp. II:53-60, 2004.
[33] A. Torralba, K. Murphy, and W. Freeman, “Sharing Features: Efficient Boosting Procedures for Multiclass Object Detection,” Proc. Int'l Conf. Computer Vision and Pattern Recognition, pp. II:762-769, 2004.
[34] R. Xiao, L. Zhu, and H.-J. Zhang, “Boosting Chain Learning for Object Detection,” Proc. Int'l Conf. Computer Vision, pp. 709-715, 2003.
[35] S. Li, Z. Zhang, H.-Y. Shum, and H. Zhang, “FloatBoost Learning for Classification,” Advances in Neural Information Processing Systems 15, pp. 993-1000, 2003.
[36] C. Liu and H.-Y. Shum, “Kullback-Leibler Boosting,” Proc. Int'l Conf. Computer Vision and Pattern Recognition, pp. I:587-594, 2003.
[37] J. Sun, J.M. Rehg, and A.F. Bobick, “Automatic Cascade Training with Perturbation Bias,” Proc. Int'l Conf. Computer Vision and Pattern Recognition, pp. II:276-283, 2004.
[38] M.J. Jones and P. Viola, “Fast Multi-View Face Detection,” Technical Report TR2003-96, Mitsubishi Electric Research Laboratories, 2003.
[39] X. Chen and A. Yuille, “Detecting and Reading Text in Natural Scenes,” Proc. Int'l Conf. Computer Vision and Pattern Recognition, pp. II:366-373, 2004.
[40] O. Carmichael and M. Hebert, “Shape-Based Recognition of Wiry Objects,” Proc. Int'l Conf. Computer Vision and Pattern Recognition, pp. II:401-408, 2003.
[41] P. Viola, M.J. Jones, and D. Snow, “Detecting Pedestrians Using Patterns of Motion and Appearance,” Proc. Int'l Conf. Computer Vision, pp. 734-741, 2003.
[42] A.R. Webb, Statistical Pattern Recognition. Oxford Univ. Press, 1999.
[43] S. Avidan and M. Butman, “The Power of Feature Clustering: An Application to Object Detection,” Advances in Neural Information Processing Systems 17, pp. 57-64, 2005.
[44] L. Ren, G. Shakhnarovich, J.K. Hodgins, H. Pfister, and P.A. Viola, “Learning Silhouette Features for Control of Human Motion,” ACM Trans. Graphics, vol. 24, no. 4, pp. 1303-1331, 2005.
[45] F. Fleuret, “Fast Binary Feature Selection with Conditional Mutual Information,” J. Machine Learning Research, vol. 5, pp. 1531-1555, 2004.
[46] S. Brubaker, J. Wu, J. Sun, M. Mullin, and J. Rehg, “On the Design of Cascades of Boosted Ensembles for Face Detection,” Technical Report GIT-GVU-05-28, GVU Center, Georgia Inst. of Tech nology, 2005.
[47] L. Mason, J. Baxter, P.L. Bartlett, and M. Frean, “Functional Gradient Techniques for Combining Hypotheses,” Advances in Large Margin Classifiers, pp. 221-246, MIT Press, 2000.
[48] G. Lanckriet, L.E. Ghaoui, C. Bhattacharyya, and M. Jordan, “A Robust Minimax Approach to Classification,” J. Machine Learning Research, vol. 3, pp. 555-582, 2002.
[49] S.-J. Kim, A. Magnani, S. Samar, S. Boyd, and J. Lim, “Pareto Optimal Linear Classification,” Proc. Int'l Conf. Machine Learning, pp. 473-480, 2006.
16 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool