1. Facial Emotion Recognition Based On Sobel-Resnet
- Author
-
Xinmin Xu, Yao Zhuang, and Xinyi Shen
- Subjects
Computer science ,business.industry ,Pattern recognition (psychology) ,Sobel operator ,Pattern recognition ,Enhanced Data Rates for GSM Evolution ,Emotion recognition ,Artificial intelligence ,business ,Facial recognition system ,Automation ,Field (computer science) ,Residual neural network - Abstract
In recent years, facial expression recognition has gained a growing attention in the field of pattern recognition research. Now many previous researches use deeper model or model integration to improve the recognition rate. For these models are more difficult to train and traditional methods have optimizable recognition accuracy, in this paper, we present a novel single network which combines the classic Resnet with the sobel features which can emphasize edge information effectively. We also adopt 10-crop testing to further improve the performance. The model was tested on the CK+ database and FER2013 database and we observed 95.96% and 71.89% classification accuracy respectively. The results showed that the method achieved better or comparable recognition rate with other state-of art methods.
- Published
- 2021
- Full Text
- View/download PDF