Facial Expression Recognition

基于跨连接 LeNet-5 网络的面部表情识别

自动化学报 2018.1

问题

• 传统的表情识别方法需要进行复杂的人工特征提取
• 为避免人为因素对表情特征提取产生的影响, 本文选择卷积神经网络

方法

• 采用改进的 LeNet-5
• 即将网络结构中提取的低层次特征与高层次特征相结合构造分类器

• JAFFE 94.37%
• CK+ 83.74%

参考

http://www.aas.net.cn/CN/abstract/abstract19213.shtml

---

基于兴趣区域深度神经网络的静态面部表情识别

电子学报 2017.5

问题

• 之前的一些方法泛化能力不佳

方法

• 用K-ROI
  
  • 测试数据采用ROI方法（DeepID里面的）划分，单个测试图像的决策通过对该图像9个ROI的判别投票来确定

参考

http://kns.cnki.net/KCMS/detail/detail.aspx?filename=dzxu201705023&dbname=CJFD&dbcode=CJFQ

---

Facial Expression Recognition Based on Complexity Perception Classification Algorithm

arXiv:1803

问题

• The different expressions of emotion and uncontrolled environmental factors lead to inconsistencies in the complexity of FER and variability of between expression categories, which is often overlooked in most facial expression recognition systems.

方法

• we presented a simple and efficient CNN model to extract facial features, and proposed a complexity perception classification (CPC) algorithm for FER.
• The CPC algorithm divided the dataset into an easy classification sample subspace and a complex classification sample subspace by evaluating the complexity of facial features that are suitable for classification
  

参考

https://arxiv.org/abs/1803.00185