摘 要：人脸表情识别是图像识别的一个重要领域。由于人脸表情较多，图像背景复杂，不同类型人脸相似，同类型人脸的差异甚小，人脸表情识别仍存在很大挑战。传统人脸识别分类方法主要基于依靠人工提取分类特征，且精度不高。本文构建基于Keras 的卷积神经网络模型，并运用FER2013 数据集，结果表明该方法提高了人脸表情识别的精度，为该问题的解决提供了新的思路和方法。
关键词：卷积神经网络；表情识别；深度学习
中图分类号：TP389.1；TP391.4 文献标识码：A 文章编号：2096-4706（2019）14-0081-03
Research on Facial Expression Recognition Based on Convolutional Neural Network
FANG Yan
（School of Mathematics and Computer Science，Quanzhou Normal University，Quanzhou 362000，China）
Abstract：Facial expression recognition is an important field of image recognition. Face expression recognition still faces great challenges because of the large number of facial expressions，the complex image background，the similarity of different types of faces and the small difference between the same types of faces. Traditional face recognition classification methods mainly rely on manual extraction of classification features，and the accuracy is not high. This paper constructs a convolutional neural network model based on Keras and applies it to FER2013 data set. The results show that this method improves the accuracy of facial expression recognition and provides a new idea and method for solving this problem.
Keywords：convolutional neural network；expression recognition；deep learning
基金项目：泉州市科技局计划项目（项目编号：2014Z135）；泉州师范学院校级自选项目（项目编号：2013KJ11）。
参考文献：
[1] Mehrabian A. Communication without words [J].Psychology Today 2，1968（4）：53-56.
[2] Ekman P. Universals and cultural differences in facial expressions of emotion [C]// Nebraska Symposium of Motivation，1972.University of Nebraska，Press，1972．
[3] Lecun Y，Bottou L，Bengio Y，et al. Gradient-based learning applied to document recognition [C]// Proceedings of the IEEE，1998，86（11）：2278-2324.
[4] Krizhevsky A，Sutskever I，Hinton G. ImageNet Classification with Deep Convolutional Neural Networks [C]// NIPS. Curran Associates Inc. 2012.
[5] Schroff F，Kalenichenko D，Philbin J. FaceNet：A unified embedding for face recognition and clustering [C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition（ CVPR）.Boston，USA，2015.
[6] Ribeiro E，Uhl A，Hafner M. Colonic Polyp Classification with Convolutional Neural Networks [C]// 2016 IEEE 29th International Symposium on Computer-Based Medical Systems （CBMS），Dublin，2016：253-258.
[7] Girshick R，Donahue J，Darrelland T，et al. Rich feature hierarchies for object detection and semantic segmentation [C]// 2014IEEE Conference on Computer Vision and Pattern Recognition，Columbus，2014：580-587.
作者简介：方彦（1981.10-），女，汉族，福建福清人，讲师，硕士，研究方向：机器学习。