Multiscale Feature Fusion Attention Lightweight Facial Expression Recognition
Facial expression recognition based on residual networks is important for technologies related to space human-robot interaction and collaboration but suffers from low accuracy and slow computation in complex network structures. To solve these problems, this paper proposes a multiscale feature fusion...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-01-01
|
| Series: | International Journal of Aerospace Engineering |
| Online Access: | http://dx.doi.org/10.1155/2022/6523234 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850178782465359872 |
|---|---|
| author | Jinyuan Ni Xinyue Zhang Jianxun Zhang |
| author_facet | Jinyuan Ni Xinyue Zhang Jianxun Zhang |
| author_sort | Jinyuan Ni |
| collection | DOAJ |
| description | Facial expression recognition based on residual networks is important for technologies related to space human-robot interaction and collaboration but suffers from low accuracy and slow computation in complex network structures. To solve these problems, this paper proposes a multiscale feature fusion attention lightweight wide residual network. The network first uses an improved random erasing method to preprocess facial expression images, which improves the generalizability of the model. The use of a modified depthwise separable convolution in the feature extraction network reduces the computational effort associated with the network parameters and enhances the characterization of the extracted features through a channel shuffle operation. Then, an improved bottleneck block is used to reduce the dimensionality of the upper layer network feature map to further reduce the number of network parameters while enhancing the network feature extraction capability. Finally, an optimized multiscale feature lightweight attention mechanism module is embedded to further improve the feature extractability of the network for human facial expressions. The experimental results show that the accuracy of the model is 73.21%, 98.72%, and 95.21% on FER2013, CK+ and JAFFE, respectively, with a covariance of 10.14 M. Compared with other networks, the model proposed in this paper has faster computing speed and better accuracy at the same time. |
| format | Article |
| id | doaj-art-c55176ac569f4df6b1bfd3f13f53de39 |
| institution | OA Journals |
| issn | 1687-5974 |
| language | English |
| publishDate | 2022-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | International Journal of Aerospace Engineering |
| spelling | doaj-art-c55176ac569f4df6b1bfd3f13f53de392025-08-20T02:18:39ZengWileyInternational Journal of Aerospace Engineering1687-59742022-01-01202210.1155/2022/6523234Multiscale Feature Fusion Attention Lightweight Facial Expression RecognitionJinyuan Ni0Xinyue Zhang1Jianxun Zhang2College of Computer Science and EngineeringSydney Smart Technology CollegeCollege of Computer Science and EngineeringFacial expression recognition based on residual networks is important for technologies related to space human-robot interaction and collaboration but suffers from low accuracy and slow computation in complex network structures. To solve these problems, this paper proposes a multiscale feature fusion attention lightweight wide residual network. The network first uses an improved random erasing method to preprocess facial expression images, which improves the generalizability of the model. The use of a modified depthwise separable convolution in the feature extraction network reduces the computational effort associated with the network parameters and enhances the characterization of the extracted features through a channel shuffle operation. Then, an improved bottleneck block is used to reduce the dimensionality of the upper layer network feature map to further reduce the number of network parameters while enhancing the network feature extraction capability. Finally, an optimized multiscale feature lightweight attention mechanism module is embedded to further improve the feature extractability of the network for human facial expressions. The experimental results show that the accuracy of the model is 73.21%, 98.72%, and 95.21% on FER2013, CK+ and JAFFE, respectively, with a covariance of 10.14 M. Compared with other networks, the model proposed in this paper has faster computing speed and better accuracy at the same time.http://dx.doi.org/10.1155/2022/6523234 |
| spellingShingle | Jinyuan Ni Xinyue Zhang Jianxun Zhang Multiscale Feature Fusion Attention Lightweight Facial Expression Recognition International Journal of Aerospace Engineering |
| title | Multiscale Feature Fusion Attention Lightweight Facial Expression Recognition |
| title_full | Multiscale Feature Fusion Attention Lightweight Facial Expression Recognition |
| title_fullStr | Multiscale Feature Fusion Attention Lightweight Facial Expression Recognition |
| title_full_unstemmed | Multiscale Feature Fusion Attention Lightweight Facial Expression Recognition |
| title_short | Multiscale Feature Fusion Attention Lightweight Facial Expression Recognition |
| title_sort | multiscale feature fusion attention lightweight facial expression recognition |
| url | http://dx.doi.org/10.1155/2022/6523234 |
| work_keys_str_mv | AT jinyuanni multiscalefeaturefusionattentionlightweightfacialexpressionrecognition AT xinyuezhang multiscalefeaturefusionattentionlightweightfacialexpressionrecognition AT jianxunzhang multiscalefeaturefusionattentionlightweightfacialexpressionrecognition |