《计算机应用研究》|Application Research of Computers

结合空洞卷积的CNN实时微表情识别算法

Real-time micro-expression recognition algorithm based on atrous convolutions for CNN

免费全文下载 (已被下载 次)  
获取PDF全文
作者 赖振意,陈人和,钱育蓉
机构 新疆大学 软件学院,乌鲁木齐 830000
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2020)12-053-3777-04
DOI 10.19734/j.issn.1001-3695.2019.07.0273
摘要 随着CNN等基于深度特征的人脸自发式微表情识别分类方法逐渐完善,相比于传统的特征提取方法更易满足应用实时性,针对微表情持续时间短、动作幅度细微,在多卷积层叠加会丢失图像中的细微信息的问题,为了完善细节信息,充分提取微表情细微特征,提出结合空洞卷积核及人脸自动校正算法,完善CNN特征提取过程,通过自动人脸矫正适应实际应用中的实时识别分类,在CASME及CASMEⅡ微表情公开数据集上完成模型训练及测试,通过损失函数方案对比提高模型鲁棒性,CASME中准确率为70.16%,CASMEⅡ中准确率为72.26%;实时识别帧率在60 fps。该方法能有效地提高微表情识别准确率,满足实时性要求,且具有较好的鲁棒性和泛化能力。
关键词 微表情识别; 空洞卷积; 表情识别; 卷积神经网络
基金项目 国家自然科学基金资助项目(61562086,61966035)
新疆维吾尔自治区教育厅创新团队项目(XJEDU2016S035)
新疆维吾尔自治区自然科学基金资助项目(2018D01C036)
新疆维吾尔自治区研究生创新项目(XJ2019G071,XJ2019G069,XJ2019G072)
本文URL http://www.arocmag.com/article/01-2020-12-053.html
英文标题 Real-time micro-expression recognition algorithm based on atrous convolutions for CNN
作者英文名 Lai Zhenyi, Chen Renhe, Qian Yurong
机构英文名 School of Software,Xinjiang University,Urumqi 830000,China
英文摘要 Based on the depth feature of facial micro-expression recognition, such as CNN, the classification method of facial micro-expression recognition is gradually improved. Compared with the traditional feature extraction method, it is easier to meet the real-time application. In order to perfect the details and extract the fine features of micro-expressions, this paper proposed a new algorithm combining the atrous convolutions kernel and the automatic correction of face to improve the feature extraction process of CNN network. It trained and tested the model on CASME and CASME Ⅱ micro-expression public data sets through real-time recognition in real-time application of automatic face correction. It improved the robustness of the model by comparing the loss function schemes. The accuracy of the method in CASME is 70.16% and witch in CASMEⅡ is 72.26%. Real-time recognition frame rate at 60 fps. This method can effectively improve the accuracy of micro-expression recognition, meet the real-time requirements, and has good robustness and generalization ability.
英文关键词 micro-expression recognition; atrous convolutions; expression recognition; CNN
参考文献 查看稿件参考文献
 
收稿日期 2019/7/31
修回日期 2019/9/11
页码 3777-3780,3835
中图分类号 TP391.41
文献标志码 A