ATNet: A Defect Detection Framework for X-ray Images of DIP Chip Lead Bonding
In order to improve the production quality and qualification rate of chips, X-ray nondestructive imaging technology has been widely used in the detection of chip defects, which represents an important part of the quality inspection of products after packaging. However, the current traditional defect...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-07-01
|
| Series: | Micromachines |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-666X/14/7/1375 |
| _version_ | 1827732353898774528 |
|---|---|
| author | Renbin Huang Daohua Zhan Xiuding Yang Bei Zhou Linjun Tang Nian Cai Han Wang Baojun Qiu |
| author_facet | Renbin Huang Daohua Zhan Xiuding Yang Bei Zhou Linjun Tang Nian Cai Han Wang Baojun Qiu |
| author_sort | Renbin Huang |
| collection | DOAJ |
| description | In order to improve the production quality and qualification rate of chips, X-ray nondestructive imaging technology has been widely used in the detection of chip defects, which represents an important part of the quality inspection of products after packaging. However, the current traditional defect detection algorithm cannot meet the demands of high accuracy, fast speed, and real-time chip defect detection in industrial production. Therefore, this paper proposes a new multi-scale feature fusion module (ATSPPF) based on convolutional neural networks, which can more fully extract semantic information at different scales. In addition, based on this module, we design a deep learning model (ATNet) for detecting lead defects in chips. The experimental results show that at 8.2 giga floating point operations (GFLOPs) and 146 frames per second (FPS), mAP<sub>0.5</sub> and mAP<sub>0.5–0.95</sub> can achieve an average accuracy of 99.4% and 69.3%, respectively, while the detection speed is faster than the baseline yolov5s by nearly 50%. |
| first_indexed | 2024-03-11T00:49:18Z |
| format | Article |
| id | doaj.art-d9470ae273bf4b61a24f4d1ef73e23be |
| institution | Directory Open Access Journal |
| issn | 2072-666X |
| language | English |
| last_indexed | 2024-03-11T00:49:18Z |
| publishDate | 2023-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Micromachines |
| spelling | doaj.art-d9470ae273bf4b61a24f4d1ef73e23be2023-11-18T20:32:34ZengMDPI AGMicromachines2072-666X2023-07-01147137510.3390/mi14071375ATNet: A Defect Detection Framework for X-ray Images of DIP Chip Lead BondingRenbin Huang0Daohua Zhan1Xiuding Yang2Bei Zhou3Linjun Tang4Nian Cai5Han Wang6Baojun Qiu7School of Mechanical and Electrical Engineering, Guangdong University of Technology, Guangzhou 510006, ChinaSchool of Mechanical and Electrical Engineering, Guangdong University of Technology, Guangzhou 510006, ChinaSchool of Mechanical and Electrical Engineering, Guangdong University of Technology, Guangzhou 510006, ChinaSchool of Mechanical and Electrical Engineering, Guangdong University of Technology, Guangzhou 510006, ChinaSchool of Mechanical and Electrical Engineering, Guangdong University of Technology, Guangzhou 510006, ChinaSchool of Information Engineering, Guangdong University of Technology, Guangzhou 510006, ChinaSchool of Mechanical and Electrical Engineering, Guangdong University of Technology, Guangzhou 510006, ChinaChina Electronic Product Reliability and Environmental Testing Research Institute, Guangzhou 511370, ChinaIn order to improve the production quality and qualification rate of chips, X-ray nondestructive imaging technology has been widely used in the detection of chip defects, which represents an important part of the quality inspection of products after packaging. However, the current traditional defect detection algorithm cannot meet the demands of high accuracy, fast speed, and real-time chip defect detection in industrial production. Therefore, this paper proposes a new multi-scale feature fusion module (ATSPPF) based on convolutional neural networks, which can more fully extract semantic information at different scales. In addition, based on this module, we design a deep learning model (ATNet) for detecting lead defects in chips. The experimental results show that at 8.2 giga floating point operations (GFLOPs) and 146 frames per second (FPS), mAP<sub>0.5</sub> and mAP<sub>0.5–0.95</sub> can achieve an average accuracy of 99.4% and 69.3%, respectively, while the detection speed is faster than the baseline yolov5s by nearly 50%.https://www.mdpi.com/2072-666X/14/7/1375chipsdefectsdeep learningX-ray images |
| spellingShingle | Renbin Huang Daohua Zhan Xiuding Yang Bei Zhou Linjun Tang Nian Cai Han Wang Baojun Qiu ATNet: A Defect Detection Framework for X-ray Images of DIP Chip Lead Bonding Micromachines chips defects deep learning X-ray images |
| title | ATNet: A Defect Detection Framework for X-ray Images of DIP Chip Lead Bonding |
| title_full | ATNet: A Defect Detection Framework for X-ray Images of DIP Chip Lead Bonding |
| title_fullStr | ATNet: A Defect Detection Framework for X-ray Images of DIP Chip Lead Bonding |
| title_full_unstemmed | ATNet: A Defect Detection Framework for X-ray Images of DIP Chip Lead Bonding |
| title_short | ATNet: A Defect Detection Framework for X-ray Images of DIP Chip Lead Bonding |
| title_sort | atnet a defect detection framework for x ray images of dip chip lead bonding |
| topic | chips defects deep learning X-ray images |
| url | https://www.mdpi.com/2072-666X/14/7/1375 |
| work_keys_str_mv | AT renbinhuang atnetadefectdetectionframeworkforxrayimagesofdipchipleadbonding AT daohuazhan atnetadefectdetectionframeworkforxrayimagesofdipchipleadbonding AT xiudingyang atnetadefectdetectionframeworkforxrayimagesofdipchipleadbonding AT beizhou atnetadefectdetectionframeworkforxrayimagesofdipchipleadbonding AT linjuntang atnetadefectdetectionframeworkforxrayimagesofdipchipleadbonding AT niancai atnetadefectdetectionframeworkforxrayimagesofdipchipleadbonding AT hanwang atnetadefectdetectionframeworkforxrayimagesofdipchipleadbonding AT baojunqiu atnetadefectdetectionframeworkforxrayimagesofdipchipleadbonding |