基于卷积神经网络局部特征融合的人脸表情识别  

Facial Expression Recognition Based on Local Feature Fusion of Convolutional Neural Network

作　　者：姚丽莎[1] 徐国明 赵凤 Yao Lisha;Xu Guoming;Zhao Feng(Institute of Information and Software,Institute of Information Engineering,Anhui Xinhua University,Hefei,Anhui 230088,China)

机构地区：[1]安徽新华学院信息工程学院信息系统软件研究所,安徽合肥230088

出　　处：《激光与光电子学进展》2020年第4期330-337,共8页Laser & Optoelectronics Progress

基　　金：安徽省高校自然科学重点研究项目(KJ2018A0587);安徽新华学院校级重点科研项目(2018zr006);安徽新华学院校级重点科研项目(2018zr001);安徽省质量工程建设项目(2018jyssf111)。

摘　　要：为提高人脸表情分类的识别率和实时性,提出一种基于卷积神经网络(CNN)局部特征融合的人脸表情识别方法。首先,构建CNN模型,学习眼睛、眉毛、嘴巴3个局部区域的局部特征;然后,将局部特征送入到支持向量机(SVM)多分类器中获取各类特征的后验概率;最后,通过粒子群寻优算法优化各特征的最优融合权值,实现正确率最优的决策级融合,完成表情分类。实验表明,本文方法在CK+和JAFFE数据库的平均识别率分别达到了94.56%和97.08%,与其他识别方法相比,本文方法性能优越,能提高算法的识别率和稳健性,同时保证了算法的实时性。Herein,a facial expression recognition method based on local feature fusion of convolutional neural network(CNN)is proposed to improve recognition rate and real-time performance of facial expression classification.First,a CNN model is constructed to learn the local features of the eyes,eyebrows,and mouth.Then,the local features are sent to a support vector machine multi-classifier to obtain their posterior probabilities.Finally,aparticle swarm optimization algorithm is used to optimize the fusion weight of each feature,realize the decision-level fusion with the optimal accuracy rate,and complete the expression classification.Experiments show that the average recognition rates of the method on the CK+and JAFFE databases are 94.56%and 97.08%,respectively.Compared with other recognition methods,results show that the proposed method has superior performance,improves the recognition rate and robustness,and ensures the real-time performance of the classification.

关 键 词：机器视觉 表情识别 卷积神经网络 决策融合 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]