A Design of Face Detection and Facial Expression Recognition Techniques Based on Boosting Schema

Abstract:

During the development of the facial expression classification procedure, we evaluate three machine learning methods. We combine ABAs with CARTs, which selects weak classifiers and integrates them into a strong classifier automatically. We have presented a highly automatic facial expression recognition system in which a face detection procedure is first able to detect and locate human faces in image sequences acquired in real environments. We need not label or choose characteristic blocks in advance. In the face detection procedure, some geometrical properties are applied to eliminate the skin color regions that do not belong to human faces. In the facial feature extraction procedure, we only perform both the binarization and edge detection operations on the proper ranges of eyes, mouth, and eyebrows to obtain the 16 landmarks of a human face to further produce 16 characteristic distances which represent a kind of expressions. We realize a facial expression classification procedure by employing an ABA to recognize six kinds of expressions. The performance of the system is very satisfactory; whose recognition rate achieves more than 90%.

• Periodical: Applied Mechanics and Materials (Volumes 121-126)
• Pages: 617-621
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.121-126.617
• Online since: October 2011
• Authors: Chang Yi Kao, Chin Shyurng Fahn
• Keywords: Adaboost Algorithm, Expression Recognition, Face Detection, Feature Extraction

References

[1] K. C. Fan, Y. K. Wang, and B. F. Chen, Introduction of tracking algorithms, Image and Recognition, Vol. 8, No. 4, pp.17-30, (2002).

[2] W. Zhao, R. Chellappa, P. J. Phillips, and A. Rosenfeld, Face recognition: a literature survey, ACM Computing Surveys, vol. 35, no. 4, pp.399-458, (2003).

DOI: 10.1145/954339.954342

[3] Foresti, G.L., Micheloni, C., Snidaro, L., and Marchiol, C.: Face detection for visual surveillance, Proc. 12th IEEE Int. Conf. Image Anal. Process., 2003, p.115─120.

DOI: 10.1109/iciap.2003.1234036

[4] Zhang, Z., Lyons, M., Schuster, M., and Akamatsu, S.: Comparison between geometry-based and gabor-wavelets-based facial expression recognition using multi-layer perceptron, Proc. IEEE Int. Conf. Automat. Face Gesture Recogni., 1998, pp.454-459.

DOI: 10.1109/afgr.1998.670990

[5] Yang, M.H., Kriegman, D., and Ahuja, N.: Detecting faces in images: a survey, IEEE Trans. Pattern Anal. Machine Intell., 2002, 24, (1), pp.34-58.

DOI: 10.1109/34.982883

[6] Yang, G., and Huang, T.S.: Human face detection in a complex background, Pattern Recogni., 1994, 27, (1), pp.53-64.

[7] Yow, K.C., and Cipolla, R.: Feature-based human face detection, Image Vision Comput., 1997, 15, (9), pp.712-735.

DOI: 10.1016/s0262-8856(97)00003-6

[8] S. L. Phung, A. Bouzerdoum, and D. Chai, A novel skin color model in YCbCr color space and its application to human face detection, in Proceedings of IEEE International Conference on Image Processing, vol. 1, pp.289-291, (2002).

DOI: 10.1109/icip.2002.1038016

[9] C. Lin, Face detection, pose classification, and face recognition based on triangle geometry and color features, Master Paper, Department of Computer Science Information Engineering, National Central University, Jhongli, Taiwan, (2001).

[10] M. Soriano, S. Huovinen, B. Martinkauppi, and M. Laaksonen, Using the skin locus to cope with changing illumination conditions in color-based face tracking, in Proceedings of the IEEE Nordic Signal Processing Symposium, pp.383-386, (2000).

DOI: 10.1109/icpr.2000.905542

[11] Sargin, M.E., Erzin, E., Yemez, Y., Tekalp, A.M., Erdem, A.T., Erdem, C., and Ozkan, M.: Prosody-driven head-gesture animation, Proc. Int. Conf. Acoust., Speech, and Signal Process., 2007, vol. 2, pp.677-680.

DOI: 10.1109/icassp.2007.366326