基于感知机制的CNN模型提升微表情识别准确率
A Perception CNN for Facial Expression Recognition
- 五路并行网络分别捕捉眼、颊、口等局部特征
- 多域交互机制融合局部与全局面部结构信息
- 两阶段损失函数提升特征精度与重建效果
卷积神经网络（CNN）可自动学习人脸图像数据模式以实现面部表情识别（FER），但常忽略面部分割的影响。本文提出一种感知CNN（PCNN），通过五路并行网络同时学习眼部、颧骨和口部的局部特征，敏感捕捉细微表情变化；引入多域交互机制，融合局部器官特征与全局面部结构特征，更全面表达人脸图像；设计两阶段损失函数，约束获取的感知信息与重建人脸图像的准确性，确保PCNN在FER任务中的性能。实验表明，该模型在多个实验室与真实场景基准（CK+、JAFFE、FER2013、FERPlus、RAF-DB及遮挡与姿态变异数据集）上均取得优异结果。代码已公开于https://github.com/hellloxiaotian/PCNN。
原文摘要 · Abstract (English)
Convolutional neural networks (CNNs) can automatically learn data patterns to express face images for facial expression recognition (FER). However, they may ignore effect of facial segmentation of FER. In this paper, we propose a perception CNN for FER as well as PCNN. Firstly, PCNN can use five parallel networks to simultaneously learn local facial features based on eyes, cheeks and mouth to realize the sensitive capture of the subtle changes in FER. Secondly, we utilize a multi-domain interaction mechanism to register and fuse between local sense organ features and global facial structural features to better express face images for FER. Finally, we design a two-phase loss function to restrict accuracy of obtained sense information and reconstructed face images to guarantee performance of obtained PCNN in FER. Experimental results show that our PCNN achieves superior results on several lab and real-world FER benchmarks: CK+, JAFFE, FER2013, FERPlus, RAF-DB and Occlusion and Pose Variant Dataset. Its code is available at https://github.com/hellloxiaotian/PCNN.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。