深度二值卷积网络的人脸表情识别方法  

Facial Expression Recognition Based on Deep Binary Convolutional Network

作　　者：周丽芳[1,2,3] 刘俊林 李伟生 米建勋[2] 雷帮军[3] Zhou Lifang;Liu Junlin;Li Weisheng;Mi Jianxun;Lei Bangjun(College of Software,Chongqing University of Posts and Telecommunications,Chongqing 400065;Key Laboratory of Image Cognition,Chongqing University of Posts and Telecommunications,Chongqing 400065;Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering,China Three Gorges University,Yichang 443002)

机构地区：[1]重庆邮电大学软件工程学院,重庆400065 [2]重庆邮电大学图像认知重庆市重点实验室,重庆400065 [3]三峡大学水电工程智能视觉监测湖北省重点实验室,宜昌443002

出　　处：《计算机辅助设计与图形学学报》2022年第3期425-436,共12页Journal of Computer-Aided Design & Computer Graphics

基　　金：重庆市教委科学技术研究项目(KJZD-K201900601);重庆市自然科学基金面上项目(cstc2019jcyj-msxm X0461);水电工程智能视觉监测湖北省重点实验室(三峡大学)开放基金(2020SDSJ01)。

摘　　要：为解决人脸表情识别时存在的参数量大、速度低和表情区域特征表示力不足的问题,提出一种基于深度二值卷积网络的人脸表情识别方法.首先设计一个二值卷积与传统卷积并行运算的轻量化网络模型BRNet,以降低网络模型参数的复杂度,从而提升识别的速度;然后构建一个动态半径策略提取表情二值特征,并形成表情区域注意权重,实现表情局部特征与人脸全局特征的有效融合;最后设计交叉熵和L2损失,快速实现了表情图像的准确分类.实验结果表明,所提方法在常用的CK+和Oulu-CASIA表情库上的平均识别率分别达到99.25%和93.85%,皆优于同类轻量级卷积网络;网络参数量和计算量为5.0×10^(5)B和2.1×10^(5)B,而EfficientFace模型的计算量约为该方法的77倍,证明了所提方法在表情识别中的有效性和轻量性.Facial expression recognition(FER) is a challenging task because of the large number of parameters,low speed and insufficient feature representation of the expression region.In order to address the above-mentioned challenges,a deep binary convolutional network for FER is proposed.Firstly,a lightweight convolution network(BRNet) with parallel operation of binary convolution and traditional convolution is designed to reduce the complexity of network and improve the speed of recognition.Secondly,a dynamic radius strategy is constructed to extract binary features and form the attention weight of expression region so that the local features and global features can be fused effectively.Finally,the cross-entropy and L2 loss are designed for quick and accurate expression classification.Experiments show that the average accuracy of the proposed method is 99.25% and 93.85% on CK+ and Oulu-CASIA respectively,which are higher than the other similar lightweight convolutional networks.The parameters and computation cost of network are 5.0×10^(5) bytes and 2.1×10^(6) bytes.In contrast,the computation cost of EfficientFace is about 77 times than proposed method.As a result,the effectiveness and lightness of proposed method have been proved.

关 键 词：二值卷积网络 局部二值模式 注意力机制 人脸表情识别 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]