期刊名称：International Journal of Electronics and Computer Science Engineering
电子版ISSN：2277-1956
出版年度：2012
卷号：1
期号：3
页码：1112-1118
出版社：Buldanshahr : IJECSE
摘要：The objective of this research is comparative study of different feature extraction techniques for facial expression recognition & develops a algorithm, for feature extraction using AdaBoost classifier to reduce the generalization error and improve performance by getting the high recognition rate. For facial feature extraction, I will follow 2 different techniques: Discrete Cosine Transform, Wavelet Transform. Upon extraction of the facial expression information the feature vector is given to facial expression classifier. An Adaboost-based classifier is be designed to deal with varies of facial expressions which are to be recognized and for the facial expression recognition JAFFE database is used
