Steel Surface Defect Detection Based on FF R-CNN
A Faster R-CNN steel surface defect detection algorithm based on feature fusion and cascade detection network was proposed to solve the problem of low detection accuracy caused by reduced structure information when Deep Learning algorithm was used to detect steel surface defects. The improved Faster...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Editorial Office of Journal of Taiyuan University of Technology
2021-09-01
|
| Series: | Taiyuan Ligong Daxue xuebao |
| Subjects: | |
| Online Access: | https://tyutjournal.tyut.edu.cn/englishpaper/show-326.html |
| _version_ | 1797216697300549632 |
|---|---|
| author | Qiang HAN Zhe ZHANG Xinying XU Xinlin XIE |
| author_facet | Qiang HAN Zhe ZHANG Xinying XU Xinlin XIE |
| author_sort | Qiang HAN |
| collection | DOAJ |
| description | A Faster R-CNN steel surface defect detection algorithm based on feature fusion and cascade detection network was proposed to solve the problem of low detection accuracy caused by reduced structure information when Deep Learning algorithm was used to detect steel surface defects. The improved Faster R-CNN algorithm is used to detect surface defects of steel. First, the feature map is extracted from the main network and fused to reduce the loss of structural information; Then the resulting feature map is further input into the RPN network generation area recommendation box; Finally, the detection network is used to classify and regress the regional recommendation box, and two detection networks are cascaded to achieve the target of accurate detection results. The model was analyzed by comparative experiments to find the algorithm model with the best detection accuracy. The proposed algorithm was tested on the NEU-DET dataset. The detection mean average precision of the backbone network using VGG-16 is 2.40% higher than that using Resnet-50. By fusing the features, the detection mean average precisionis improved by 11.86%. By detecting the cascade of the network, the detection mean average precision is improved by 2.37%. By continuously improving and optimizing the algorithm model, the detection mean average precision reaches 98.29%. Compared with traditional steel surface detection methods, this algorithm can detect the types and locations of steel surface defects more accurately, and improve the detection accuracy of steel surface defects. |
| first_indexed | 2024-04-24T11:50:05Z |
| format | Article |
| id | doaj.art-5a9adf3d2c964545889f00989451ddd8 |
| institution | Directory Open Access Journal |
| issn | 1007-9432 |
| language | English |
| last_indexed | 2024-04-24T11:50:05Z |
| publishDate | 2021-09-01 |
| publisher | Editorial Office of Journal of Taiyuan University of Technology |
| record_format | Article |
| series | Taiyuan Ligong Daxue xuebao |
| spelling | doaj.art-5a9adf3d2c964545889f00989451ddd82024-04-09T08:04:06ZengEditorial Office of Journal of Taiyuan University of TechnologyTaiyuan Ligong Daxue xuebao1007-94322021-09-0152575476310.16355/j.cnki.issn1007-9432tyut.2021.05.0091007-9432(2021)05-0754-10Steel Surface Defect Detection Based on FF R-CNNQiang HAN0Zhe ZHANG1Xinying XU2Xinlin XIE3College of Electrical and Power Engineering, Taiyuan University of Technology, Taiyuan 030024, ChinaCollege of Electrical and Power Engineering, Taiyuan University of Technology, Taiyuan 030024, ChinaCollege of Electrical and Power Engineering, Taiyuan University of Technology, Taiyuan 030024, ChinaKey Lab of Advanced Control and Intelligent Equipment of Shanxi, Taiyuan University of Science and Technology, Taiyuan 030024, ChinaA Faster R-CNN steel surface defect detection algorithm based on feature fusion and cascade detection network was proposed to solve the problem of low detection accuracy caused by reduced structure information when Deep Learning algorithm was used to detect steel surface defects. The improved Faster R-CNN algorithm is used to detect surface defects of steel. First, the feature map is extracted from the main network and fused to reduce the loss of structural information; Then the resulting feature map is further input into the RPN network generation area recommendation box; Finally, the detection network is used to classify and regress the regional recommendation box, and two detection networks are cascaded to achieve the target of accurate detection results. The model was analyzed by comparative experiments to find the algorithm model with the best detection accuracy. The proposed algorithm was tested on the NEU-DET dataset. The detection mean average precision of the backbone network using VGG-16 is 2.40% higher than that using Resnet-50. By fusing the features, the detection mean average precisionis improved by 11.86%. By detecting the cascade of the network, the detection mean average precision is improved by 2.37%. By continuously improving and optimizing the algorithm model, the detection mean average precision reaches 98.29%. Compared with traditional steel surface detection methods, this algorithm can detect the types and locations of steel surface defects more accurately, and improve the detection accuracy of steel surface defects.https://tyutjournal.tyut.edu.cn/englishpaper/show-326.htmlsurface defect detection of steeldeep learningfaster r-cnnfeature fusioncascade detection network |
| spellingShingle | Qiang HAN Zhe ZHANG Xinying XU Xinlin XIE Steel Surface Defect Detection Based on FF R-CNN Taiyuan Ligong Daxue xuebao surface defect detection of steel deep learning faster r-cnn feature fusion cascade detection network |
| title | Steel Surface Defect Detection Based on FF R-CNN |
| title_full | Steel Surface Defect Detection Based on FF R-CNN |
| title_fullStr | Steel Surface Defect Detection Based on FF R-CNN |
| title_full_unstemmed | Steel Surface Defect Detection Based on FF R-CNN |
| title_short | Steel Surface Defect Detection Based on FF R-CNN |
| title_sort | steel surface defect detection based on ff r cnn |
| topic | surface defect detection of steel deep learning faster r-cnn feature fusion cascade detection network |
| url | https://tyutjournal.tyut.edu.cn/englishpaper/show-326.html |
| work_keys_str_mv | AT qianghan steelsurfacedefectdetectionbasedonffrcnn AT zhezhang steelsurfacedefectdetectionbasedonffrcnn AT xinyingxu steelsurfacedefectdetectionbasedonffrcnn AT xinlinxie steelsurfacedefectdetectionbasedonffrcnn |