结合卷积神经网络与OpenCV的人脸表情识别  

Facial Expression Recognition Combining Convolutional Neural Network and OpenCV

作　　者：张悦欣 付晓峰[1] ZHANG Yue-xin;FU Xiao-feng(School of Computer Science and Technology,Hangzhou Dianzi University,Hangzhou 310018,China)

机构地区：[1]杭州电子科技大学计算机学院,浙江杭州310018

出　　处：《电脑知识与技术》2021年第5期183-185,共3页Computer Knowledge and Technology

基　　金：国家自然科学基金资助项目(61672199);浙江省科技计划项目-2018年度重点研发计划项目(2018C01030)。

摘　　要：针对实时人脸表情识别模型训练慢、识别速度慢的问题,提出一种OpenCV和卷积神经网络结合进行实时表情识别的方法。人脸表情是多个局部区域特征的集合,而卷积神经网络提取出的特征能更多地关注局部,因此采取卷积神经网络的方式进行模型的训练。所提网络在全连接层中加入了Dropout,能有效预防过拟合现象的发生,并且提升模型泛化能力。实验结果表明此模型的可行性,在fer2013数据集上的准确率达到71.6%。基于以上方法再结合OpenCV构建一个实时表情识别系统,系统实时识别表情的速度为0.4s。所构建的系统相比于现有的其他系统,具有训练速度较快、准确率较高、识别速度较快等优点。Aiming at the problems of slow training and slow recognition speed of real-time facial expression recognition model,a method for real-time expression recognition by combining OpenCV and convolutional neural network is proposed.Facial expres⁃sion is a collection of features of multiple local regions,and the features extracted by the convolutional neural network can pay more attention to the locality.Therefore,this paper adopts the method of convolutional neural network to train the model.The net⁃work in this paper adds Dropout to the fully connected layer,which can effectively prevent the occurrence of overfitting and im⁃prove the model generalization ability.The experimental results show the feasibility of this model,and the accuracy rate on the fer2013 data set reaches 71.6%.Based on the above method and then combined with OpenCV to construct the real-time expression recognition system in this paper,the system's real-time expression recognition speed is 0.4s.Compared with the existing system,the system in this paper has the advantages of faster training speed,higher accuracy and faster recognition speed.

关 键 词：OPENCV 卷积神经网络 表情识别 情感分类 深度学习 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]