Sewing gesture image detection method based on improved SSD model
Abstract In this letter, the authors present a novel sewing gesture image detection method based on an improved single shot MultiBox detector (SSD) model. The deeper Resnet50 residual network replaces the VGG16 basic network of the original SSD model to improve the feature extraction ability. High a...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-04-01
|
| Series: | Electronics Letters |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/ell2.12149 |
| _version_ | 1811269722616889344 |
|---|---|
| author | Wenjie Wang Mengling He Xiaohua Wang Weiming Yao |
| author_facet | Wenjie Wang Mengling He Xiaohua Wang Weiming Yao |
| author_sort | Wenjie Wang |
| collection | DOAJ |
| description | Abstract In this letter, the authors present a novel sewing gesture image detection method based on an improved single shot MultiBox detector (SSD) model. The deeper Resnet50 residual network replaces the VGG16 basic network of the original SSD model to improve the feature extraction ability. High and low level features are fused based on a feature pyramid network (FPN) for enhanced small‐target detection performance. The model is trained via transfer learning to resolve the small sample shortage problem. The proposed model shows an average precision of 88.69% on a sewing gesture data set constructed by the authors. The proposed model outperforms the Faster R‐CNN, YOLO, and SSD networks in terms of accuracy with acceptable operating speed on the same data set and fully satisfies the real‐time requirements for sewing gesture detection. |
| first_indexed | 2024-04-12T21:48:15Z |
| format | Article |
| id | doaj.art-07b81c1412ad4a90a5b374e1523e5008 |
| institution | Directory Open Access Journal |
| issn | 0013-5194 1350-911X |
| language | English |
| last_indexed | 2024-04-12T21:48:15Z |
| publishDate | 2021-04-01 |
| publisher | Wiley |
| record_format | Article |
| series | Electronics Letters |
| spelling | doaj.art-07b81c1412ad4a90a5b374e1523e50082022-12-22T03:15:34ZengWileyElectronics Letters0013-51941350-911X2021-04-0157832132310.1049/ell2.12149Sewing gesture image detection method based on improved SSD modelWenjie Wang0Mengling He1Xiaohua Wang2Weiming Yao3School of Electronics and Information Xi'an Polytechnic University Xi'an P. R. ChinaSchool of Electronics and Information Xi'an Polytechnic University Xi'an P. R. ChinaSchool of Electronics and Information Xi'an Polytechnic University Xi'an P. R. ChinaSchool of Electronics and Information Xi'an Polytechnic University Xi'an P. R. ChinaAbstract In this letter, the authors present a novel sewing gesture image detection method based on an improved single shot MultiBox detector (SSD) model. The deeper Resnet50 residual network replaces the VGG16 basic network of the original SSD model to improve the feature extraction ability. High and low level features are fused based on a feature pyramid network (FPN) for enhanced small‐target detection performance. The model is trained via transfer learning to resolve the small sample shortage problem. The proposed model shows an average precision of 88.69% on a sewing gesture data set constructed by the authors. The proposed model outperforms the Faster R‐CNN, YOLO, and SSD networks in terms of accuracy with acceptable operating speed on the same data set and fully satisfies the real‐time requirements for sewing gesture detection.https://doi.org/10.1049/ell2.12149Optical, image and video signal processingComputer vision and image processing techniquesNeural nets |
| spellingShingle | Wenjie Wang Mengling He Xiaohua Wang Weiming Yao Sewing gesture image detection method based on improved SSD model Electronics Letters Optical, image and video signal processing Computer vision and image processing techniques Neural nets |
| title | Sewing gesture image detection method based on improved SSD model |
| title_full | Sewing gesture image detection method based on improved SSD model |
| title_fullStr | Sewing gesture image detection method based on improved SSD model |
| title_full_unstemmed | Sewing gesture image detection method based on improved SSD model |
| title_short | Sewing gesture image detection method based on improved SSD model |
| title_sort | sewing gesture image detection method based on improved ssd model |
| topic | Optical, image and video signal processing Computer vision and image processing techniques Neural nets |
| url | https://doi.org/10.1049/ell2.12149 |
| work_keys_str_mv | AT wenjiewang sewinggestureimagedetectionmethodbasedonimprovedssdmodel AT menglinghe sewinggestureimagedetectionmethodbasedonimprovedssdmodel AT xiaohuawang sewinggestureimagedetectionmethodbasedonimprovedssdmodel AT weimingyao sewinggestureimagedetectionmethodbasedonimprovedssdmodel |