Research on the Algorithm of Semi-supervised Robust Facial Expression Recognition
Under the condition of multi-databases, a novel algorithm of facial expression recognition was proposed to improve the robustness of traditional semi-supervised methods dealing with individual differences in facial expression recognition. First, the regions of interest of facial expression images were determined by face detection and facial expression features were extracted using Linear Discriminant Analysis. Then Transfer Learning Adaptive Boosting (TrAdaBoost) algorithm was improved as semi-supervised learning method for multi-classification. The results show that the proposed method has stronger robustness than the traditional methods, and improves the facial expression recognition rate from multiple databases.
KeywordsFacial Expression Recognition Semi-Supervised Learning TrAdaBoost
Unable to display preview. Download preview PDF.
- 1.Jiang, B., Jia, K.B., Yang, G.S.: Research Advance of Facial Expression Recognition. Computer Science 38, 25–31 (2011)Google Scholar
- 2.Luo, S.W.: The Perception Computing of Visual Information. Science Press, Beijing (2010)Google Scholar
- 3.Abdel Hady, M.F., Schels, M., Schwenker, F., Palm, G.: Semi-supervised facial expressions annotation using co-training with fast probabilistic tri-class SVMs. In: Diamantaras, K., Duch, W., Iliadis, L.S. (eds.) ICANN 2010, Part II. LNCS, vol. 6353, pp. 70–75. Springer, Heidelberg (2010)CrossRefGoogle Scholar
- 5.Tan, H.C., Zhang, Y.J.: Person-Independent Facial Expression Recognition Based on Person-Similarity Weighted Distance. Jounal of Electronics & Information Technology 29, 455–459 (2007)Google Scholar
- 6.Zhou, Z.H., Yang, Q.: Machine learning and its applications. Tsinghua University Press, Beijing (2011)Google Scholar
- 7.Yan Jr., H.B., Ang, M.H., Poo, A.N.: Cross-Dataset Facial Expression Recognition. In: IEEE International Conference on Robotics and Automation, pp. 5985–5990. IEEE Press, Shanghai (2011)Google Scholar
- 8.Dai, W.Y., Yang, Q., Xue, G.R., et al.: Boosting for Transfer Learning. In: 24th International Conference on Machine Learning, pp. 193–200. Omni Press, Corvallis (2007)Google Scholar
- 13.Zhu, X.J., Ghahramani, Z.: Learning from labeled and unlabeled data with label propagation. Technical Report, Carnegie Mellon University (2002)Google Scholar
- 14.Chen, K., Wang, S.H.: Regularized Boost for Semi-Supervised Learning. In: 21st Conference on Neural Information Processing Systems, pp. 281–288. MIT Press, Cambridge (2007)Google Scholar