A survey of facial expression recognition based on deep learning
Authors:
- 9 November 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 90-94
Abstract
Facial expression recognition is the key research direction in many fields such as machine vision, pattern recognition and artificial intelligence. lt has become a research hotspot of many scholars and experts. This paper gives a comprehensive overview of deep expression recognition from image preprocessing, common expression recognition networks, and common expression databases. Then we review the current design and training strategies of deep neural networks based on static images and dynamic images, and discuss their advantages and limitations. Finally, the future challenges and corresponding opportunities in the field are analyzed, as well as the future direction of deep learning expression recognition systems.Keywords
Funding Information
- National Natural Science Foundation of China
This publication has 11 references indexed in Scilit:
- Learning supervised scoring ensemble for emotion recognition in the wild2017
- A new deep learning method based on AlexNet model and SSD model for tennis ball recognition2017
- CNN-Based cascaded multi-task learning of high-level prior and density estimation for crowd counting2017
- Adaptive Deep Metric Learning for Identity-Aware Facial Expression Recognition2017
- Facial Expression Recognition Using Enhanced Deep 3D Convolutional Neural Networks2017
- Peak-Piloted Deep Network for Facial Expression Recognition2016
- LBF Based 3D Regression for Facial Animation2016
- Joint Face Detection and Alignment Using Multitask Cascaded Convolutional NetworksIEEE Signal Processing Letters, 2016
- Emotion Recognition in the Wild via Convolutional Neural Networks and Mapped Binary Patterns2015
- Robust Discriminative Response Map Fitting with Constrained Local Models2013