基于CNN和LSTM的人脸表情识别模型设计  

Facial expression recognition model design based on CNN and LSTM

作　　者：程换新[1] 王雪 程力 孙胜意 Cheng Huanxin;Wang Xue;Cheng Li;Sun Shengyi(College of Automation and Electronic Engineering,Qingdao University of Science and Technology,Qingdao 266061,China)

机构地区：[1]青岛科技大学自动化与电子工程学院,青岛266061

出　　处：《电子测量技术》2021年第17期160-164,共5页Electronic Measurement Technology

基　　金：国家海洋局重大专项(国海科字[2016]494号No.30)资助。

摘　　要：人脸表情能够正确地反映人的内心活动,但由于表情的复杂性和微妙性,准确地识别人脸表情仍然是一大难题。本文设计了一种基于卷积神经网络(CNN)和长短期记忆神经网络(LSTM)的方法让计算机能够识别人脸的表情,损失函数采用Focal loss。该框架包括3个方面:采用两种不同的预处理技术处理光照变化,并保留图像的边缘信息;预处理后的图像被输入到两个独立的CNN层用于提取特征;将提取到的特征与LSTM层融合。使用FER2013、JAFFE和CK+3个数据集验证模型准确性,并选择FER2013数据集制作混合矩阵,结果为该模型在FER2013数据集上的准确率相比于目前先进模型提升了9.65%,在JAFFE和CK+数据集上也表现良好,结果表明所提出的模型具有较强的泛化能力。Facial expressions can correctly reflect people′s inner activities, but due to the complexity and subtlety of facial expressions, accurate recognition of facial expressions is still a big problem. This paper designs a method based on convolutional neural network(CNN) and long short term memory(LSTM), so that the computer can recognize the expression of human face the loss function uses Focal loss. The framework includes three aspects: two different preprocessing techniques are used to deal with the illumination change and preserve the edge information of the image. The preprocessed image is input into two independent CNN layers for feature extraction. The extracted features are fused with LSTM layer. Using FER2013, JAFFE and CK+data sets to verify the accuracy of the model, and select FER2013 data set to make a mixed matrix. The results show that the accuracy of the model on FER2013 data set is improved by 9.65% compared with the current advanced model, and it also performs well on JAFFE and CK+data sets. The results show that the proposed model has strong generalization ability.

关 键 词：人脸表情 CNN LSTM Focal loss 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]