Convolutional Neural Network Defect Detection Algorithm for Wire Bonding X-ray Images
To address the challenges of complex backgrounds, small defect sizes, and diverse defect types in defect detection of wire bonding X-ray images, this paper proposes a convolutional-neural-network-based defect detection method called YOLO-CSS. This method designs a novel feature extraction network th...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Micromachines |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-666X/14/9/1737 |
| _version_ | 1827725264242606080 |
|---|---|
| author | Daohua Zhan Renbin Huang Kunran Yi Xiuding Yang Zhuohao Shi Ruinan Lin Jian Lin Han Wang |
| author_facet | Daohua Zhan Renbin Huang Kunran Yi Xiuding Yang Zhuohao Shi Ruinan Lin Jian Lin Han Wang |
| author_sort | Daohua Zhan |
| collection | DOAJ |
| description | To address the challenges of complex backgrounds, small defect sizes, and diverse defect types in defect detection of wire bonding X-ray images, this paper proposes a convolutional-neural-network-based defect detection method called YOLO-CSS. This method designs a novel feature extraction network that effectively captures semantic features from different gradient information. It utilizes a self-adaptive weighted multi-scale feature fusion module called SMA which adaptively weights the contribution of detection results based on different scales of feature maps. Simultaneously, skip connections are employed at the bottleneck of the network to ensure the integrity of feature information. Experimental results demonstrate that on the wire bonding X-ray defect image dataset, the proposed algorithm achieves mAP 0.5 and mAP 0.5–0.95 values of 97.3% and 72.1%, respectively, surpassing the YOLO series algorithms. It also exhibits certain advantages in terms of model size and detection speed, effectively balancing detection accuracy and speed. |
| first_indexed | 2024-03-10T22:26:57Z |
| format | Article |
| id | doaj.art-58bafb49575d412282ee04307955f4e5 |
| institution | Directory Open Access Journal |
| issn | 2072-666X |
| language | English |
| last_indexed | 2024-03-10T22:26:57Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Micromachines |
| spelling | doaj.art-58bafb49575d412282ee04307955f4e52023-11-19T11:59:57ZengMDPI AGMicromachines2072-666X2023-09-01149173710.3390/mi14091737Convolutional Neural Network Defect Detection Algorithm for Wire Bonding X-ray ImagesDaohua Zhan0Renbin Huang1Kunran Yi2Xiuding Yang3Zhuohao Shi4Ruinan Lin5Jian Lin6Han Wang7State Key Laboratory of Precision Electronic Manufacturing Technology and Equipment, Guangzhou 510006, ChinaState Key Laboratory of Precision Electronic Manufacturing Technology and Equipment, Guangzhou 510006, ChinaState Key Laboratory of Precision Electronic Manufacturing Technology and Equipment, Guangzhou 510006, ChinaState Key Laboratory of Precision Electronic Manufacturing Technology and Equipment, Guangzhou 510006, ChinaState Key Laboratory of Precision Electronic Manufacturing Technology and Equipment, Guangzhou 510006, ChinaState Key Laboratory of Precision Electronic Manufacturing Technology and Equipment, Guangzhou 510006, ChinaState Key Laboratory of Precision Electronic Manufacturing Technology and Equipment, Guangzhou 510006, ChinaState Key Laboratory of Precision Electronic Manufacturing Technology and Equipment, Guangzhou 510006, ChinaTo address the challenges of complex backgrounds, small defect sizes, and diverse defect types in defect detection of wire bonding X-ray images, this paper proposes a convolutional-neural-network-based defect detection method called YOLO-CSS. This method designs a novel feature extraction network that effectively captures semantic features from different gradient information. It utilizes a self-adaptive weighted multi-scale feature fusion module called SMA which adaptively weights the contribution of detection results based on different scales of feature maps. Simultaneously, skip connections are employed at the bottleneck of the network to ensure the integrity of feature information. Experimental results demonstrate that on the wire bonding X-ray defect image dataset, the proposed algorithm achieves mAP 0.5 and mAP 0.5–0.95 values of 97.3% and 72.1%, respectively, surpassing the YOLO series algorithms. It also exhibits certain advantages in terms of model size and detection speed, effectively balancing detection accuracy and speed.https://www.mdpi.com/2072-666X/14/9/1737convolutional neural networkX-ray imageswire bonding defectsYOLO-CSS |
| spellingShingle | Daohua Zhan Renbin Huang Kunran Yi Xiuding Yang Zhuohao Shi Ruinan Lin Jian Lin Han Wang Convolutional Neural Network Defect Detection Algorithm for Wire Bonding X-ray Images Micromachines convolutional neural network X-ray images wire bonding defects YOLO-CSS |
| title | Convolutional Neural Network Defect Detection Algorithm for Wire Bonding X-ray Images |
| title_full | Convolutional Neural Network Defect Detection Algorithm for Wire Bonding X-ray Images |
| title_fullStr | Convolutional Neural Network Defect Detection Algorithm for Wire Bonding X-ray Images |
| title_full_unstemmed | Convolutional Neural Network Defect Detection Algorithm for Wire Bonding X-ray Images |
| title_short | Convolutional Neural Network Defect Detection Algorithm for Wire Bonding X-ray Images |
| title_sort | convolutional neural network defect detection algorithm for wire bonding x ray images |
| topic | convolutional neural network X-ray images wire bonding defects YOLO-CSS |
| url | https://www.mdpi.com/2072-666X/14/9/1737 |
| work_keys_str_mv | AT daohuazhan convolutionalneuralnetworkdefectdetectionalgorithmforwirebondingxrayimages AT renbinhuang convolutionalneuralnetworkdefectdetectionalgorithmforwirebondingxrayimages AT kunranyi convolutionalneuralnetworkdefectdetectionalgorithmforwirebondingxrayimages AT xiudingyang convolutionalneuralnetworkdefectdetectionalgorithmforwirebondingxrayimages AT zhuohaoshi convolutionalneuralnetworkdefectdetectionalgorithmforwirebondingxrayimages AT ruinanlin convolutionalneuralnetworkdefectdetectionalgorithmforwirebondingxrayimages AT jianlin convolutionalneuralnetworkdefectdetectionalgorithmforwirebondingxrayimages AT hanwang convolutionalneuralnetworkdefectdetectionalgorithmforwirebondingxrayimages |