高级检索

    王德勋, 虞慧群, 范贵生. 基于深度学习的面部动作单元识别算法[J]. 华东理工大学学报(自然科学版), 2020, 46(2): 269-276. DOI: 10.14135/j.cnki.1006-3080.20190107003
    引用本文: 王德勋, 虞慧群, 范贵生. 基于深度学习的面部动作单元识别算法[J]. 华东理工大学学报(自然科学版), 2020, 46(2): 269-276. DOI: 10.14135/j.cnki.1006-3080.20190107003
    WANG Dexun, YU Huiqun, FAN Guisheng. Facial Action Unit Recognition Algorithm Based on Deep Learning[J]. Journal of East China University of Science and Technology, 2020, 46(2): 269-276. DOI: 10.14135/j.cnki.1006-3080.20190107003
    Citation: WANG Dexun, YU Huiqun, FAN Guisheng. Facial Action Unit Recognition Algorithm Based on Deep Learning[J]. Journal of East China University of Science and Technology, 2020, 46(2): 269-276. DOI: 10.14135/j.cnki.1006-3080.20190107003

    基于深度学习的面部动作单元识别算法

    Facial Action Unit Recognition Algorithm Based on Deep Learning

    • 摘要: 面部动作单元识别任务是理解人脸表情最重要的环节之一,但因为类别极度不平衡和属于多标签分类等问题,给算法设计带来了不小的困难。针对这些问题设计了一种基于深度学习的面部动作单元识别算法。首先,基于迁移学习理论,以人脸识别任务为目标驱动,使用大规模数据集预训练卷积网络,使模型具有提取人脸抽象特征的能力;其次,设计了一个根据分类置信度来动态加权样本损失大小的目标函数,使得模型更关注于优化少数类样本;最后,结合多标签共现关系拟合和人脸关键点回归两个相关任务,联合训练模型并测试。实验结果表明,该方法在CK+和MMI数据集上能有效提升分类正确率与F1分数。

       

      Abstract: Facial action unit recognition task is one of the most important aspects of understanding facial expressions. However, the extremely unbalanced categories and the multi-label classification bring great difficulties for the design of recognition algorithm. By means of deep learning technique, this paper proposes a face action unit recognition algorithm. Firstly, based on the transfer learning theory and driven by the face recognition task, some large-scale datasets are used to pre-train the convolutional network so as to make this model has the ability to extract abstract features of face. Secondly, an objective function is designed to dynamically weigh the sample loss according to the classification confidence for making the model focus more on optimizing a few samples. Finally, two related tasks including the multi-label co-occurrence relationship fitting and the key-point regression of face are combined to jointly train and test the model. It is shown from the experimental results that the proposed method can effectively improve the classification accuracy and F1-score on the relevant datasets CK+ and MMI.

       

    /

    返回文章
    返回