Facial expression recognition based on
Adaboost-Gaussian process classification
LI Wen-shu1, HE Fang-fang1, QIAN Yun-tao2, ZHOU Chang-le3
1. College of Information Science and Technology, Zhejiang Sci-Tech University, Hangzhou 310018, China;
2. College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China; 3. Institute of
Artificial Intelligence, Xiamen University, Xiamen 361005, China
By using the Gaussian process classifier’s advantages of high classification accuracy and low computational complexity, an improved expression recognition method was proposed in order to modify the Adaboost’s disadvantage of poor classification accuracy and long time consuming. The facial expression recognition algorithm combines Gaussian process classification (GPC) with Adaboost. The algorithm uses the Gaussian process classifier as weak classifier when training Adaboost. Then these weak classifiers are combined into an overall classification, and the Adaboost is extended into a multiclass classification algorithm. Gabor wavelet transformation is used to extract facial expressional features, since the highdimensional Gabor features are redundant; the two-dimensional principal component analysis (2DPCA) is used to select these features. Experimental results based on the Cohn-Kanade database and JAFFE database show that the accuracy and recognition speed of the algorithm are inspiring．
LI Wen-shu, HE Fang-fang, QIAN Yun-tao, ZHOU Chang-le. Facial expression recognition based on
Adaboost-Gaussian process classification. J4, 2012, 46(1): 79-83.
［1］ TIAN Y, KANADE T, COHN J. Evaluation of Gabor waveletbased facial action unit recognition in image sequences of increasing complexity ［C］∥Proceedings of IEEE International Conference on Automatic Face and Gesture Recognition. Washington: IEEE, 2002: 26-30．
［2］ MULLER S, WALLHOFF F, HULSKEN F, et al. Facial expression recognition using pseudo 3D hidden Markov models ［C］∥Proceedings of International Conference on Pattern Recognition. Québec City: ［s.n.］, 2002: 32-35．
［3］ ZHANG Y, JI Q. Active and dynamic information fusion for facial expression understanding from image sequences ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence，2005, 27(5): 699-714．
［4］ KAPPOR A, QI Y, PICARD R W. Fully automatic upper facial action recognition ［C］∥ Proceedings of Analysis and Modeling of Faces and Gestures. Nice, France: ［s.n.］, 2003: 195-202．
［5］ LIU C, SHUM H Y. KullbackLeibler boosting ［C］ ∥Proceedings of Computer Society Conference on Computer Vision and Pattern Recognition. Wisconsin: IEEE, 2003: 587-594．
［6］ BARTLETT M S, LITTLEWOET G, FRANK M, et al. Recognizing facial expression: machine learning and application to spontaneous behavior ［C］∥Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego: IEEE, 2005: 568-573．
［7］ PANTIC M, ROTHKRANTZ L. Facial action recognition for facial expression analysis from static face images ［J］. IEEE Transactions on Systems, Man and Cybernetics：Part B, 2004, 34 (3): 1449-1461．
［8］ CHELLAPPA R, WILSON C L, SIROHEY S. Human and machine recognition of faces: a survey ［C］∥Proceedings of the IEEE. ［S.l.］: IEEE, 1995: 705-740．
［9］ PANTIC M, ROT H K, RANTZ L J M. Automatic analysis of facial expressions: the state of the art ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence，2000, 22(12):1424-1445．
［10］ 杨康, 陈晓, 彭国华. 基于统计学习的人脸表情分类［J］. 计算机仿真, 2009, 26(6): 237-241．
YANG Kang, CHEN Xiao, PENG Guohua. Facial expression classification based on statistical study ［J］. Computer Simulation, 2009, 26(6): 237-241．
［11］ 罗飞, 王国胤, 杨勇. 一种基于Gabor小波特征的人脸表情识别新方法［J］. 计算机学习,2009, 36(1): 181-215．
LUO Fei, WANG Guoyin, YANG Yong. New approach for facial expression recognition based on Gabor feature ［J］. Computer Science, 2009, 36(1): 181-215．
［12］ HAYRAN C, HUPET L, CZYZ J, et al. Independent component analysis for face authentication ［C］∥Proceedings of KnowledgeBased Intelligent Information and Engineering Systems. Crema: ［s.n.］, 2002: 1207-1211．
［13］ CHENG J, YING Z. Facial expression recognition based on 2D PCA ［J］.Computer Engineering and Applications, 2006, 31 (5): 32-39．
［14］ 王雪松, 张依阳, 程玉虎. 基于高斯过程分类器的连续空间强化学习［J］. 电子学报, 2009, 37（6）: 1153-1158．
WANG Xuesong, ZHANG Yiyang, CHENG Yuhu. Reinforcement learning for continuous spaces based on Gaussian process classifier ［J］. Act Electronica Sinica, 2009, 37（6）: 1153-1158．
［15］ CARL E R, CHRISTOP K I W. Gaussian processes for machine learning ［M］. ［S.l.］: MIT, 2006: 41-48．
［16］ 张晓龙, 任芳. 支持向量机与Adaboost的结合算法研究［J］. 计算机应用研究, 2009, 26(1): 78-80．
ZHANG Xiaolong, REN Fang. Study on combinability of SVM and Adaboost algorithm ［J］. Application Research of Computers, 2009, 26(1): 78-80．
［17］ 王宇博, 艾海舟, 武勃, 等. 人脸表情的实时分类［J］.计算机辅助设计与图形学学报, 2005, 17(6): 1296-1301．
WANG Yubo, AI Haizhou, WU bo, et al. Realtime facial expression classification ［J］. Journal of ComputerAided Design and Computer Graphics, 2005, 17 (6): 1296-1301.
［18］ KOTSIA I, PITAS I. Facial expression recognition in image sequences using geometric deformation features and support vector machines ［J］. IEEE Transactions on Image Processing, 2007, 16(1): 172-187．
［19］ ZHANG H, BERG A C, MAIRE M, et al. SVMKNN: discriminative nearest neighbor classification for visual category recognition ［C］∥Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2006: 2126-2136．
［20］ KANADE T, COHN J F, TIAN Y L. Comprehensive database for facial expression analysis ［C］∥ Proceedings of IEEE International Conference on Face and Gesture Recognition. Grenoble: IEEE, 2000: 46-53．
