A Discriminative Learning Convolutional Neural Network For Facial Expression Recognition
PROCEEDINGS OF 2017 3RD IEEE INTERNATIONAL CONFERENCE ON COMPUTER AND COMMUNICATIONS (ICCC)(2017)
Abstract
In recent years, deep learning has become a hot research area. The research on facial recognition is progressing rapidly, however, facial expression recognition faces many difficulties due to poor robustness and real-time performance. The feature of several different kind of facial expression is similar, which is easy to confuse, and it became the key factor to affect the accuracy of facial expression recognition. At the same time, Convolutional Neural Network (CNN) has been widely used in image classification tasks by its powerful ability on distributed abstract feature extraction in the field of image. This paper designs and realizes a discriminative learning convolution neural network. The network combines the central loss function and the verification-recognition model, which make the model have better characteristics of the generalization and discrimination ability, and also reduce the misclassification in facial expression recognition. Experiments show that the accuracy of the designed facial expression recognition network has been effectively improved.
MoreTranslated text
Key words
CNN, center loss, verification-identification model, facial expression recognition
AI Read Science
Must-Reading Tree
Example
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined