Recognition of Teachers’ Facial Expression Intensity Based on Convolutional Neural Network and Attention Mechanism
The evaluations of traditional teaching quality are mainly subjective, and there is a lack of fine-grained objective data to support the evaluation of teaching states in the classroom. In this paper, an intensity-based facial expression dataset is proposed and named EIDB-13, which contains 13 kinds...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9301312/ |
| _version_ | 1818917811018268672 |
|---|---|
| author | Kun Zheng Dong Yang Junhua Liu Jinling Cui |
| author_facet | Kun Zheng Dong Yang Junhua Liu Jinling Cui |
| author_sort | Kun Zheng |
| collection | DOAJ |
| description | The evaluations of traditional teaching quality are mainly subjective, and there is a lack of fine-grained objective data to support the evaluation of teaching states in the classroom. In this paper, an intensity-based facial expression dataset is proposed and named EIDB-13, which contains 13 kinds and 10393 facial images collected from thousands of individuals and existing facial expression datasets. Convolutional neural network (CNN) and attention mechanism are combined to recognize facial expressions. Migration learning is used to solve over-fitting problem in the process of training deep network based on the small sample dataset. InceptionResNetV2 is employed as migration network. Furthermore, an InceptionResNetV2+CBAM network proposed extract similar feature information among facial expressions and it outperforms the network without attention mechanisms. Experiments show a classification accuracy rate of 78% on the intensity-based facial expression dataset EIDB-13 and of 88% on the public macro expression dataset RAF-DB. Combining facial expression recognition technology into teaching is a key foundation to study teaching quality on the intensity of teacher's expression. |
| first_indexed | 2024-12-20T00:40:00Z |
| format | Article |
| id | doaj.art-9f0c56ca72a7425bb971567eb2621dac |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-20T00:40:00Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-9f0c56ca72a7425bb971567eb2621dac2022-12-21T19:59:38ZengIEEEIEEE Access2169-35362020-01-01822643722644410.1109/ACCESS.2020.30462259301312Recognition of Teachers’ Facial Expression Intensity Based on Convolutional Neural Network and Attention MechanismKun Zheng0https://orcid.org/0000-0002-8966-1184Dong Yang1Junhua Liu2Jinling Cui3Faculty of Information Technology, Beijing University of Technology, Beijing, ChinaFaculty of Information Technology, Beijing University of Technology, Beijing, ChinaFaculty of Information Technology, Beijing University of Technology, Beijing, ChinaFaculty of Information Technology, Beijing University of Technology, Beijing, ChinaThe evaluations of traditional teaching quality are mainly subjective, and there is a lack of fine-grained objective data to support the evaluation of teaching states in the classroom. In this paper, an intensity-based facial expression dataset is proposed and named EIDB-13, which contains 13 kinds and 10393 facial images collected from thousands of individuals and existing facial expression datasets. Convolutional neural network (CNN) and attention mechanism are combined to recognize facial expressions. Migration learning is used to solve over-fitting problem in the process of training deep network based on the small sample dataset. InceptionResNetV2 is employed as migration network. Furthermore, an InceptionResNetV2+CBAM network proposed extract similar feature information among facial expressions and it outperforms the network without attention mechanisms. Experiments show a classification accuracy rate of 78% on the intensity-based facial expression dataset EIDB-13 and of 88% on the public macro expression dataset RAF-DB. Combining facial expression recognition technology into teaching is a key foundation to study teaching quality on the intensity of teacher's expression.https://ieeexplore.ieee.org/document/9301312/Attention mechanismconvolutional neural networkexpression recognitionintensity of facial expression |
| spellingShingle | Kun Zheng Dong Yang Junhua Liu Jinling Cui Recognition of Teachers’ Facial Expression Intensity Based on Convolutional Neural Network and Attention Mechanism IEEE Access Attention mechanism convolutional neural network expression recognition intensity of facial expression |
| title | Recognition of Teachers’ Facial Expression Intensity Based on Convolutional Neural Network and Attention Mechanism |
| title_full | Recognition of Teachers’ Facial Expression Intensity Based on Convolutional Neural Network and Attention Mechanism |
| title_fullStr | Recognition of Teachers’ Facial Expression Intensity Based on Convolutional Neural Network and Attention Mechanism |
| title_full_unstemmed | Recognition of Teachers’ Facial Expression Intensity Based on Convolutional Neural Network and Attention Mechanism |
| title_short | Recognition of Teachers’ Facial Expression Intensity Based on Convolutional Neural Network and Attention Mechanism |
| title_sort | recognition of teachers x2019 facial expression intensity based on convolutional neural network and attention mechanism |
| topic | Attention mechanism convolutional neural network expression recognition intensity of facial expression |
| url | https://ieeexplore.ieee.org/document/9301312/ |
| work_keys_str_mv | AT kunzheng recognitionofteachersx2019facialexpressionintensitybasedonconvolutionalneuralnetworkandattentionmechanism AT dongyang recognitionofteachersx2019facialexpressionintensitybasedonconvolutionalneuralnetworkandattentionmechanism AT junhualiu recognitionofteachersx2019facialexpressionintensitybasedonconvolutionalneuralnetworkandattentionmechanism AT jinlingcui recognitionofteachersx2019facialexpressionintensitybasedonconvolutionalneuralnetworkandattentionmechanism |