基于多特征集成分类器的人脸表情识别

摘要

提出基于多特征集成分类器的人脸表情识别新算法.新算法首先对预处理后的人脸表情图像通过3种不同的特征提取方法来提取不同类型的表情特征,然后对不同特征构造不同的分类器,最后构造一个基于神经网络的集成分类器模型,对这3个分类器的输出进行决策融合,从而实现人脸表情的最终识别.在JAFFE人脸表情数据库中的试验结果表明,所提算法的识别效果优于单个特征和单一的分类器.%A multi-feature and combining multiple classifiers method for facial expression recognition was proposed. First,three features are obtained from pre-processed face images by three different feature extraction methods. Then different classitiers are made based on different features. At last, a model of combining multiple classifiers is developed based on nerve net.The outputs of three classifiers are input to the model in order to get facial expression recognition. Experimental results on JAFFE database show that proposed method is superior to the single feature and single classifier.