摘要
研究人脸表情识别,赋予计算机情感理解和情感表达的能力在人机交互与情感计算中具有重要的意义.本文提出了一种基于HOG特征的表情识别方法.首先提取人脸表情图像的梯度方向直方图(HOG)特征,对得到的特征利用主成份分析(PCA)方法进行降维,然后用支持向量机分类.在JAFFE人脸表情数据库上的实验表明,与传统的人脸表情识别算法相比,该方法能获得更高的识别率.
Understanding facial expression recognition and then assigning ability of emotion understanding and expression to the computer is an important subject in human-computer interaction and affective computing. In this paper, a method for facial expression recognition based on HOG features is proposed. First, histograms of oriented gradient(HOG) features are extracted. Then, principle component analysis(PCA) is used to reduce the dimension of HOG features. Finally, SVM is used for classification. The experimental results based on JAFFE database of facial images show that our algorithm have higher accurate recognition rate than some other widely used methods.
出处
《河北工业大学学报》
CAS
北大核心
2013年第6期39-42,共4页
Journal of Hebei University of Technology
基金
河北省科学技术重大支撑计划(10243554D)
关键词
人脸表情识别
HOG特征
主成分分析
支持向量机
face expression recognition
HOG features
principle component analysis(PCA)
support vector machine(SVM)
