An Improved YOLOv7-Tiny-Based Algorithm for Wafer Surface Defect Detection
Wafer surface defect detection is a critical component in the chip manufacturing process. To address the shortcomings of manual inspection and the limitations of existing machine learning methods, this paper proposes a wafer defect detection algorithm based on an improved YOLOv7-tiny. First, a coord...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10836686/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832592967044431872 |
|---|---|
| author | Mengyun Li Xueying Wang Hongtao Zhang Xiaofeng Hu |
| author_facet | Mengyun Li Xueying Wang Hongtao Zhang Xiaofeng Hu |
| author_sort | Mengyun Li |
| collection | DOAJ |
| description | Wafer surface defect detection is a critical component in the chip manufacturing process. To address the shortcomings of manual inspection and the limitations of existing machine learning methods, this paper proposes a wafer defect detection algorithm based on an improved YOLOv7-tiny. First, a coordinate attention (CA) module is incorporated into the feature extraction network to enhance the network’s ability to learn features at defect locations. Next, a lightweight convolutional module, ghost shuffle convolution (GSConv), is introduced into the feature fusion network to reduce the network’s parameter count while maintaining a certain level of detection accuracy. Finally, the loss function is optimized by adopting IoU with minimum points distance (MPDIoU) to address issues such as small sizes and dense distributions. Experiments conducted on a self-constructed dataset show that the improved algorithm achieved a mean Average Precision (mAP) of 90.1%, representing a 3.2% increase over the original algorithm. The model size is only 5.85MB and the detection speed has been effectively enhanced, providing valuable insights for research in industrial real-time detection applications. |
| format | Article |
| id | doaj-art-e493e523a9cb42778d8d8d9fbbfbce2b |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-e493e523a9cb42778d8d8d9fbbfbce2b2025-01-21T00:01:05ZengIEEEIEEE Access2169-35362025-01-0113107241073410.1109/ACCESS.2025.352824210836686An Improved YOLOv7-Tiny-Based Algorithm for Wafer Surface Defect DetectionMengyun Li0https://orcid.org/0009-0008-3488-7240Xueying Wang1Hongtao Zhang2Xiaofeng Hu3College of Metrology Measurement and Instrument, China Jiliang University, Hangzhou, Zhejiang, ChinaCollege of Metrology Measurement and Instrument, China Jiliang University, Hangzhou, Zhejiang, ChinaZhejiang Sanhua Automotive Components Company Ltd., Hangzhou, Zhejiang, ChinaCollege of Metrology Measurement and Instrument, China Jiliang University, Hangzhou, Zhejiang, ChinaWafer surface defect detection is a critical component in the chip manufacturing process. To address the shortcomings of manual inspection and the limitations of existing machine learning methods, this paper proposes a wafer defect detection algorithm based on an improved YOLOv7-tiny. First, a coordinate attention (CA) module is incorporated into the feature extraction network to enhance the network’s ability to learn features at defect locations. Next, a lightweight convolutional module, ghost shuffle convolution (GSConv), is introduced into the feature fusion network to reduce the network’s parameter count while maintaining a certain level of detection accuracy. Finally, the loss function is optimized by adopting IoU with minimum points distance (MPDIoU) to address issues such as small sizes and dense distributions. Experiments conducted on a self-constructed dataset show that the improved algorithm achieved a mean Average Precision (mAP) of 90.1%, representing a 3.2% increase over the original algorithm. The model size is only 5.85MB and the detection speed has been effectively enhanced, providing valuable insights for research in industrial real-time detection applications.https://ieeexplore.ieee.org/document/10836686/YOLOv7-tinysilicon waferobject detectiondeep learning |
| spellingShingle | Mengyun Li Xueying Wang Hongtao Zhang Xiaofeng Hu An Improved YOLOv7-Tiny-Based Algorithm for Wafer Surface Defect Detection IEEE Access YOLOv7-tiny silicon wafer object detection deep learning |
| title | An Improved YOLOv7-Tiny-Based Algorithm for Wafer Surface Defect Detection |
| title_full | An Improved YOLOv7-Tiny-Based Algorithm for Wafer Surface Defect Detection |
| title_fullStr | An Improved YOLOv7-Tiny-Based Algorithm for Wafer Surface Defect Detection |
| title_full_unstemmed | An Improved YOLOv7-Tiny-Based Algorithm for Wafer Surface Defect Detection |
| title_short | An Improved YOLOv7-Tiny-Based Algorithm for Wafer Surface Defect Detection |
| title_sort | improved yolov7 tiny based algorithm for wafer surface defect detection |
| topic | YOLOv7-tiny silicon wafer object detection deep learning |
| url | https://ieeexplore.ieee.org/document/10836686/ |
| work_keys_str_mv | AT mengyunli animprovedyolov7tinybasedalgorithmforwafersurfacedefectdetection AT xueyingwang animprovedyolov7tinybasedalgorithmforwafersurfacedefectdetection AT hongtaozhang animprovedyolov7tinybasedalgorithmforwafersurfacedefectdetection AT xiaofenghu animprovedyolov7tinybasedalgorithmforwafersurfacedefectdetection AT mengyunli improvedyolov7tinybasedalgorithmforwafersurfacedefectdetection AT xueyingwang improvedyolov7tinybasedalgorithmforwafersurfacedefectdetection AT hongtaozhang improvedyolov7tinybasedalgorithmforwafersurfacedefectdetection AT xiaofenghu improvedyolov7tinybasedalgorithmforwafersurfacedefectdetection |