Abstract
Cascades of boosted ensembles have become a popular technique for face detection following their introduction by Viola and Jones. Researchers have sought to improve upon the original approach by incorporating new techniques such as alternative boosting methods, feature sets, etc. We explore several avenues that have not yet received adequate attention: global cascade learning, optimal ensemble construction, stronger weak hypotheses, and feature filtering. We describe a probabilistic model for cascade performance and its use in a fully-automated training algorithm.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Blanchard, G., Geman, D.: Sequential testing designs for pattern recognition. Annals of Statistics 33(3), 1155–1202 (2005)
Brubaker, S.C., Wu, J., Sun, J., Mullin, M.D., Rehg, J.M.: On the design of cascades of boosted ensembles for face detection. Technical Report GIT-GVU-05-28, Georgia Institute of Technology (2005)
Elad, M., Hel-Or, Y., Keshet, R.: Pattern detection using a maximal rejection classifier. Pattern Recognition Letters 23(12), 1459–1471 (2002)
Fan, W., Stolfo, S.J., Zhang, J., Chan, P.K.: Adacost: Misclassification cost-sensitive boosting. In: Proc. 16th Int’l Conf Machine Learning, pp. 97–105 (1999)
Fleuret, F.: Fast binary feature selection with conditional mutual information. J. Mach. Learn. Res. 5, 1531–1555 (2004)
Froba, B., Ernst, A.: Face detection with the modified census transform. In: 6th IEEE Int’l Conf. Automatic Face and Gesture Recognition, pp. 91–96 (May 2004)
Fukunaga, K.: Introduction to Statistical Pattern Recognition. Academic Press, San Diego (1990)
Gupta, A.K., Nadarajah, S. (eds.): Handbook of Beta Distribution and its applications. Marcel Dekker, Inc., New York (2004)
Guyon, I., Elisseeff, A.: An introduction to variable and feature selection. J. Mach. Learn. Res. 3, 1157–1182 (2003)
Heisele, B., Serre, T., Mukherjee, S., Poggio, T.: Feature reduction and hierarchy of classifiers for fast object detection in video images. In: CVPR, vol. II, pp. 18–24 (2001)
Huang, K., Yang, H., King, I., Lyu, M.R.: Learning classifiers from imbalanced data based on biased minimax probability machine. In: CVPR, vol.II, pp. 558–563 (2004)
Karakoulas, G.J., Shawe-Taylor, J.: Optimizing classifiers for imbalanced training sets. In: NIPS 11, pp. 253–259 (1999)
Keren, D., Osadchy, M., Gotsman, C.: Antifaces: A novel, fast method for image detection. IEEE Trans. on PAMI 23(7), 747–761 (2001)
Levi, K., Weiss, Y.: Learning object detection from a small number of examples: The importance of good features. In: CVPR, vol.II, pp. 53–60 (2004)
Li, S.Z., Zhang, Z.Q.: Floatboost learning and statistical face detection. IEEE Trans. on PAMI 26(9), 1112–1123 (2004)
Lienhart, R., Kuranov, A., Pisarevsky, V.: Empirical Analysis of Detection Cascades of Boosted Classifiers for Rapid Object Detection. In: Michaelis, B., Krell, G. (eds.) DAGM 2003. LNCS, vol. 2781, pp. 297–304. Springer, Heidelberg (2003)
Liu, C., Shum, H.-Y.: Kullback-leibler boosting. In: CVPR, vol. II, pp. 587–594 (2003)
Luo, H.: Optimization design of cascaded classifiers. In: CVPR, vol.I, pp. 480–485 (2005)
Romdhani, S., Torr, P., Schoelkopf, B., Blake, A.: Computationally efficient face detection. In: Proc. ICCV, pp. 695–700 (2001)
Schapire, R.E., Singer, Y.: Improved boosting using confidence-rated predictions. Machine Learning 37(3), 297–336 (1999)
Schneiderman, H.: Feature-centric evaluation for efficient cascaded object detection. In: CVPR, vol. II, pp. 29–36 (2004)
Sun, J., Rehg, J.M., Bobick, A.F.: Automatic cascade training with perturbation bias. In: CVPR, vol. II, pp. 276–283 (2004)
Sung, K., Poggio, T.: Example-based learning for view-based human face detection. IEEE Trans. on PAMI 20(1), 39–51 (1998)
Ting, K.M.: A comparative study of cost-sensitive boosting algorithms. In: Proc. 17th Int’l. Conf. Machine Learning, pp. 983–990 (2000)
Vasconcelos, N.: Feature selection by maximum marginal diversity: Optimality and implications for visual recognition. In: CVPR, vol.1, pp. 762–772 (2003)
Vidal-Naquet, M., Ullman, S.: Object recognition with informative features and linear classification. In: Proc. ICCV, pp. 281–288 (2003)
Viola, P., Jones, M.: Fast and robust classification using asymmetric AdaBoost and a detector cascade. In: NIPS 14, pp. 1311–1318 (2002)
Viola, P., Jones, M.J.: Robust real-time object detection. Technical Report CRL 2001/01, Compaq Cambridge Research Laboratory (February 2001)
Viola, P., Jones, M.J.: Robust real-time face detection. Int. J. Comput. Vision 57(2), 137–154 (2004)
Wu, J., Brubaker, S.C., Mullin, M.D., Rehg, J.M.: Fast asymmetric learning for cascade face detection. Technical Report GIT-GVU-05-27, Georgia Institute of Technology (2005)
Wu, J., Mullin, M., Rehg, J.: Linear asymmetric classifier for cascade detectors. In: Proc. 22nd Int’l Conf. Machine Learning, pp. 993–1000 (2005)
Wu, J., Rehg, J.M., Mullin, M.D.: Learning a rare event detection cascade by direct feature selection. In: NIPS 16, pp. 1523–1530 (2004)
Xiao, R., Zhu, L., Zhang, H.-J.: Boosting chain learning for object detection. In: Proc. ICCV, vol. 1, pp. 709–715 (2003)
Yang, M.-H., Kriegman, D.J., Ahuja, N.: Detecting faces in images: A survey. IEEE Trans. on PAMI 24(1), 34–58 (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Brubaker, S.C., Wu, J., Sun, J., Mullin, M.D., Rehg, J.M. (2006). Towards the Optimal Training of Cascades of Boosted Ensembles. In: Ponce, J., Hebert, M., Schmid, C., Zisserman, A. (eds) Toward Category-Level Object Recognition. Lecture Notes in Computer Science, vol 4170. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11957959_16
Download citation
DOI: https://doi.org/10.1007/11957959_16
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-68794-8
Online ISBN: 978-3-540-68795-5
eBook Packages: Computer ScienceComputer Science (R0)