A high-effective multitask surface defect detection method based on CBAM and atrous convolution
Given the shortcomings of conventional machine vision-based surface defect detection methods, including their low accuracy, long development cycle, and poor generalization ability, this paper proposes a surface defect detection model based on the convolutional block attention module and atrous convo...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
The Japan Society of Mechanical Engineers
2022-11-01
|
| Series: | Journal of Advanced Mechanical Design, Systems, and Manufacturing |
| Subjects: | |
| Online Access: | https://www.jstage.jst.go.jp/article/jamdsm/16/6/16_2022jamdsm0063/_pdf/-char/en |
| _version_ | 1828066686422482944 |
|---|---|
| author | Xin XIE Lei XU Xinlei LI Bin WANG Tiancheng WAN |
| author_facet | Xin XIE Lei XU Xinlei LI Bin WANG Tiancheng WAN |
| author_sort | Xin XIE |
| collection | DOAJ |
| description | Given the shortcomings of conventional machine vision-based surface defect detection methods, including their low accuracy, long development cycle, and poor generalization ability, this paper proposes a surface defect detection model based on the convolutional block attention module and atrous convolution. This model combines the surface defect segmentation task of the product with the classification task, obtains contextual information of the image at multiple scales using atrous spatial pyramid pooling, and then uses the convolutional block attention module to reallocate the weighting of the network to enhance focus on the defect area and improve the discrimination of extracted features. In addition, atrous convolution was introduced in the deep network to simplify the model when used in defect segmentation tasks and enhances the real-time performance of the model defect detection method. Experiments show the superior accuracy and real-time performance of the proposed model when compared with current mainstream surface defect detection methods and indicate its wide applicability in the detection of surface defects in industrial products. |
| first_indexed | 2024-04-10T23:35:11Z |
| format | Article |
| id | doaj.art-8f006a5a76d84634bf7ceaf315b23691 |
| institution | Directory Open Access Journal |
| issn | 1881-3054 |
| language | English |
| last_indexed | 2024-04-10T23:35:11Z |
| publishDate | 2022-11-01 |
| publisher | The Japan Society of Mechanical Engineers |
| record_format | Article |
| series | Journal of Advanced Mechanical Design, Systems, and Manufacturing |
| spelling | doaj.art-8f006a5a76d84634bf7ceaf315b236912023-01-12T00:42:28ZengThe Japan Society of Mechanical EngineersJournal of Advanced Mechanical Design, Systems, and Manufacturing1881-30542022-11-01166JAMDSM0063JAMDSM006310.1299/jamdsm.2022jamdsm0063jamdsmA high-effective multitask surface defect detection method based on CBAM and atrous convolutionXin XIE0Lei XU1Xinlei LI2Bin WANG3Tiancheng WAN4School of Information Engineering, East China Jiaotong UniversitySchool of Information Engineering, East China Jiaotong UniversitySchool of Information Engineering, East China Jiaotong UniversitySchool of Information Engineering, East China Jiaotong UniversitySchool of Information Engineering, East China Jiaotong UniversityGiven the shortcomings of conventional machine vision-based surface defect detection methods, including their low accuracy, long development cycle, and poor generalization ability, this paper proposes a surface defect detection model based on the convolutional block attention module and atrous convolution. This model combines the surface defect segmentation task of the product with the classification task, obtains contextual information of the image at multiple scales using atrous spatial pyramid pooling, and then uses the convolutional block attention module to reallocate the weighting of the network to enhance focus on the defect area and improve the discrimination of extracted features. In addition, atrous convolution was introduced in the deep network to simplify the model when used in defect segmentation tasks and enhances the real-time performance of the model defect detection method. Experiments show the superior accuracy and real-time performance of the proposed model when compared with current mainstream surface defect detection methods and indicate its wide applicability in the detection of surface defects in industrial products.https://www.jstage.jst.go.jp/article/jamdsm/16/6/16_2022jamdsm0063/_pdf/-char/enconvolutional block attention moduleatrous convolutionatrous spatial pyramid poolingsurface defect detectiondeep learning |
| spellingShingle | Xin XIE Lei XU Xinlei LI Bin WANG Tiancheng WAN A high-effective multitask surface defect detection method based on CBAM and atrous convolution Journal of Advanced Mechanical Design, Systems, and Manufacturing convolutional block attention module atrous convolution atrous spatial pyramid pooling surface defect detection deep learning |
| title | A high-effective multitask surface defect detection method based on CBAM and atrous convolution |
| title_full | A high-effective multitask surface defect detection method based on CBAM and atrous convolution |
| title_fullStr | A high-effective multitask surface defect detection method based on CBAM and atrous convolution |
| title_full_unstemmed | A high-effective multitask surface defect detection method based on CBAM and atrous convolution |
| title_short | A high-effective multitask surface defect detection method based on CBAM and atrous convolution |
| title_sort | high effective multitask surface defect detection method based on cbam and atrous convolution |
| topic | convolutional block attention module atrous convolution atrous spatial pyramid pooling surface defect detection deep learning |
| url | https://www.jstage.jst.go.jp/article/jamdsm/16/6/16_2022jamdsm0063/_pdf/-char/en |
| work_keys_str_mv | AT xinxie ahigheffectivemultitasksurfacedefectdetectionmethodbasedoncbamandatrousconvolution AT leixu ahigheffectivemultitasksurfacedefectdetectionmethodbasedoncbamandatrousconvolution AT xinleili ahigheffectivemultitasksurfacedefectdetectionmethodbasedoncbamandatrousconvolution AT binwang ahigheffectivemultitasksurfacedefectdetectionmethodbasedoncbamandatrousconvolution AT tianchengwan ahigheffectivemultitasksurfacedefectdetectionmethodbasedoncbamandatrousconvolution AT xinxie higheffectivemultitasksurfacedefectdetectionmethodbasedoncbamandatrousconvolution AT leixu higheffectivemultitasksurfacedefectdetectionmethodbasedoncbamandatrousconvolution AT xinleili higheffectivemultitasksurfacedefectdetectionmethodbasedoncbamandatrousconvolution AT binwang higheffectivemultitasksurfacedefectdetectionmethodbasedoncbamandatrousconvolution AT tianchengwan higheffectivemultitasksurfacedefectdetectionmethodbasedoncbamandatrousconvolution |