人脸表情识别（facial expression recognition,简称FER）作为智能化人机交互技术中的一个重要组成部分,近年来得到了广泛的关注,涌现出许多新方法.本文综述了国内外近4年人脸表情识别（FER）技术的最新发展.首先,介绍了FER系统的组成：人脸检测、表情特征提取和表情分类,并详细叙述了其中表情特征提取和表情分类的方法.然后,对目前广泛应用的人脸表情数据库进行了介绍,并在此基础上对当前一些FER系统的性能进行了比较分析.最后,对FER领域的研究现状和挑战给予了评述,对FER可能的发展方向进行了讨论.

As an important part of the technology for human-machine interface,facial expression recognition(FER) have drawn much attention recently and numerous methods have been proposed.In this paper,we present the up to date development of this area in recent years.First,the three steps of the FER system are introduced: face detection,expressional feature extraction and expression classification.Second,the methods of feature extraction and expression classification are detailed in different categories.Then,we also introduce the facial expression databases which are widely used at present.Based on these databases, a comparison of the performances of several FER systems is presented.At last,we demonstrate the state of the FER technique and the possible challenges,and provide some advice about the current of FER development.