Robust Multi-view Face Detection Using Error Correcting Output Codes
Abstract
This paper presents a novel method to solve multi-view face detection problem by Error Correcting Output Codes (ECOC). The motivation is that face patterns can be divided into separated classes across views, and ECOC multi-class method can improve the robustness of multi-view face detection compared with the view-based methods because of its inherent error-tolerant ability. One key issue with ECOC-based multi-class classifier is how to construct effective binary classifiers. Besides applying ECOC to multi-view face detection, this paper emphasizes on designing efficient binary classifiers by learning informative features through minimizing the error rate of the ensemble ECOC multi-class classifier. Aiming at designing efficient binary classifiers, we employ spatial histograms as the representation, which provide an over-complete set of optional features that can be efficiently computed from the original images. In addition, the binary classifier is constructed as a coarse to fine procedure using fast histogram matching followed by accurate Support Vector Machine (SVM). The experimental results show that the proposed method is robust to multi-view faces, and achieves performance comparable to that of state-of-the-art approaches to multi-view face detection.
Keywords
Support Vector Machine Base Classifier Face Detection Binary Classifier Support Vector Machine ClassificationReferences
- 1.Yang, M.H., Kriegman, D.J., Abuja, N.: Detecting Faces in Images: A Survey. IEEE Transactions on Pattern Analysis And Machine Intelligence 24(1), 34–58 (2002)CrossRefGoogle Scholar
- 2.Rowley, H.A., Baluja, S., Kanade, T.: Neural Network-Based Face Detection. IEEE Transactions on Pattern Analysis And Machine Intelligence 20(1), 29–38 (1998)CrossRefGoogle Scholar
- 3.Garcia, C., Delakis, M.: Convolutional Face Finder: A Neural Architecture for Fast and Robust Face Detection. IEEE Transactions on Pattern Analysis And Machine Intelligence 26(11), 1408–1423 (2004)CrossRefGoogle Scholar
- 4.Sung, K.K., Poggio, T.: Example-Based Learning for View-Based Human Face Detection. IEEE Transactions on Pattern Analysis And Machine Intelligence 20(1), 39–50 (1998)CrossRefGoogle Scholar
- 5.Osuna, E., Freund, R., Girosi, F.: Training Support Vector Machines: an Application to Face Detection. In: Proceedings of CVPR, pp. 130–136 (1997)Google Scholar
- 6.Romdhani, S., Torr, P., Scholkopf, B., Blake, A.: Computationally efficient face detection. In: Proceedings of the 8th International Conference on Computer Vision, vol. 2, pp. 695–700 (2001)Google Scholar
- 7.Schneiderman, H., Kanade, T.: A Statistical Method for 3D Object Detection Applied to Faces and Cars. In: IEEE Conference on Computer Vision and Pattern Recognition (2000)Google Scholar
- 8.Viola, P., Jones, M.: Robust Real Time Object Detection. In: IEEE ICCV Workshop on Statistical and Computational Theories of Vision (2001)Google Scholar
- 9.Li, S.Z., Zhang, Z.Q.: FloatBoost Learning and Statistical Face Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence 9(26), 1112–1123 (2004)CrossRefGoogle Scholar
- 10.Yow, K.C., Cipolla, R.: Feature-Based Human Face Detection. CUED/F-INFENG/TR 249 (1996)Google Scholar
- 11.Jones, M., Viola, P.: Fast Multi-view face detection. Technical Report TR2003-96, Mitsubishi Electric Research Laboratories (2003)Google Scholar
- 12.Rowley, H.A., Baluja, S., Kanade, T.: Rotation Invariant Neural Network-Based Face Detection. Computer Vision and Pattern Recognition, 38–44 (1998)Google Scholar
- 13.Li, Y.M., Gong, S.G., Liddell, H.: Support vector regression and classification based multi-view face detection and recognition. In: Proceeding of Fourth IEEE International Conference on Face and Gesture Recognition, pp. 300–305 (2000)Google Scholar
- 14.Osadchy, M., Miller, M.L., LeCun, Y.: Synergistic Face Detection and Pose Estimation with Energy-Based Models. In: Neural Information Processing Systems Conference (2004)Google Scholar
- 15.Dietterich, T.G., Bakiri, G.: Error-correcting output codes: A general method for improving multi-class inductive learning programs. In: Proceedings of the Ninth National Conference on Artificial Intelligence (AAAI 1991), pp. 572–577. AAAI Press, Menlo Park (1991)Google Scholar
- 16.Dieteerich, T.G., Bakiri, G.: Solving multi-class learning problems via error correcting output codes. Journal of Artificial Intelligence Research 2, 263–286 (1995)zbMATHGoogle Scholar
- 17.Ghani, R.: Using error-correcting codes for text classification. In: Proceedings of ICML 2000, 17th International Conference on Machine Learning, pp. 303–310 (2000)Google Scholar
- 18.Kittler, J., Ghaderi, R., Windeatt, T., Matas, J.: Face verification via error correcting output codes. Image and Vision Computing 21(13-14), 1163–1169 (2003)CrossRefGoogle Scholar
- 19.Mahamud, S., Hebert, M., Shi, J.: Object recognition using boosted discriminants. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2001 (2001)Google Scholar
- 20.Swain, M., Ballard, D.: Color indexing. International Journal of Computer Vision 7(1), 11–32 (1991)CrossRefGoogle Scholar
- 21.Zhang, H.M., Gao, W., Chen, X.L., Zhao, D.B.: Learning Informative Features for Spatial Histogram-Based Object Detection. In: Proceedings of International Joint Conference on Neural Networks 2005, pp. 1806–1811 (2005)Google Scholar
- 22.Vapnik, V.: Statistical Learning Theory. Wiley, New York (1998)zbMATHGoogle Scholar