本科论文英文翻译.pdf

Proceedings of the Eighth International Conference on Machine Learning and Cybernetics, Baoding, 12-15 July 2009 AN APPROACH FOR FACIAL EXPRESSION RECOGNITION BASED ON NEURAL NETWORK ENSEMBLE XUE-FEI BAI, WEN-JIAN WANG School of Computer and Information Technology, Shanxi University Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education Taiyuan, 030006, China E-MAIL: baixuefei@, wjwang@ Abstract: Pantic et al. [2] and Fasel et al. [3] provided in-depth This paper proposes a novel method for facial expression reviews of the research on automatic facial expression recognition based on neural network ensemble. The facial recognition from different aspects, and they systematically expression features are extracted firstly through summarized the classical technologies and methods of multi-expression eigenspace analysis, and then several neural pattern recognition and feature extraction used in FER in networks are trained each with an eigenspace of different recent years. Principal component analysis (PCA), also expressions respectively. At last their training results are aggregated as inputs of the ensemble classifier, which will known as Karhunen-Loeve expansion, is an efficient feature provide not only the final recognition results but also the extraction and representation technique widely used in the estimat