Algorithm of Computer Mainboard Quality Detection for Real-Time Based on QD-YOLO
Automated industrial quality detection (QD) boosts quality-detection efficiency and reduces costs. However, current quality-detection algorithms have drawbacks such as low efficiency, easily missed detections, and false detections. We propose QD-YOLO, an attention-based method to enhance quality-det...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-08-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/11/15/2424 |
| _version_ | 1797414169623920640 |
|---|---|
| author | Guangming Tu Jiaohua Qin Neal N. Xiong |
| author_facet | Guangming Tu Jiaohua Qin Neal N. Xiong |
| author_sort | Guangming Tu |
| collection | DOAJ |
| description | Automated industrial quality detection (QD) boosts quality-detection efficiency and reduces costs. However, current quality-detection algorithms have drawbacks such as low efficiency, easily missed detections, and false detections. We propose QD-YOLO, an attention-based method to enhance quality-detection efficiency on computer mainboards. Firstly, we propose a composite attention module for the network’s backbone to highlight appropriate feature channels and improve the feature fusion structure, allowing the network to concentrate on the crucial information in the feature map. Secondly, we employ the Meta-ACON activation function to dynamically learn whether the activation function is linear or non-linear for various input data and adapt it to varied input scenarios with varying linearity. Additionally, we adopt Ghost convolution instead of ordinary convolution, using linear operations as possible to reduce the number of parameters and speed up detection. Experimental results show that our method can achieve improved real-time performance and accuracy on the self-created mainboard quality defect dataset, with a mean average precision (mAP) of 98.85% and a detection speed of 31.25 Frames Per Second (FPS). Compared with the original YOLOv5s model, the improved method improves mAP@0.5 by 2.09% and detection speed by 2.67 FPS. |
| first_indexed | 2024-03-09T05:29:11Z |
| format | Article |
| id | doaj.art-46df034821b749e0899f6ecc1b734549 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-09T05:29:11Z |
| publishDate | 2022-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-46df034821b749e0899f6ecc1b7345492023-12-03T12:33:55ZengMDPI AGElectronics2079-92922022-08-011115242410.3390/electronics11152424Algorithm of Computer Mainboard Quality Detection for Real-Time Based on QD-YOLOGuangming Tu0Jiaohua Qin1Neal N. Xiong2College of Computer & Information Engineering, Central South University of Forestry and Technology, Changsha 410004, ChinaCollege of Computer & Information Engineering, Central South University of Forestry and Technology, Changsha 410004, ChinaDepartment of Computer Science and Mathematics, Sul Ross State University, Alpine, TX 79832, USAAutomated industrial quality detection (QD) boosts quality-detection efficiency and reduces costs. However, current quality-detection algorithms have drawbacks such as low efficiency, easily missed detections, and false detections. We propose QD-YOLO, an attention-based method to enhance quality-detection efficiency on computer mainboards. Firstly, we propose a composite attention module for the network’s backbone to highlight appropriate feature channels and improve the feature fusion structure, allowing the network to concentrate on the crucial information in the feature map. Secondly, we employ the Meta-ACON activation function to dynamically learn whether the activation function is linear or non-linear for various input data and adapt it to varied input scenarios with varying linearity. Additionally, we adopt Ghost convolution instead of ordinary convolution, using linear operations as possible to reduce the number of parameters and speed up detection. Experimental results show that our method can achieve improved real-time performance and accuracy on the self-created mainboard quality defect dataset, with a mean average precision (mAP) of 98.85% and a detection speed of 31.25 Frames Per Second (FPS). Compared with the original YOLOv5s model, the improved method improves mAP@0.5 by 2.09% and detection speed by 2.67 FPS.https://www.mdpi.com/2079-9292/11/15/2424deep learningYOLOcomposite attentioncomputer mainboard quality detectionreal-time detection |
| spellingShingle | Guangming Tu Jiaohua Qin Neal N. Xiong Algorithm of Computer Mainboard Quality Detection for Real-Time Based on QD-YOLO Electronics deep learning YOLO composite attention computer mainboard quality detection real-time detection |
| title | Algorithm of Computer Mainboard Quality Detection for Real-Time Based on QD-YOLO |
| title_full | Algorithm of Computer Mainboard Quality Detection for Real-Time Based on QD-YOLO |
| title_fullStr | Algorithm of Computer Mainboard Quality Detection for Real-Time Based on QD-YOLO |
| title_full_unstemmed | Algorithm of Computer Mainboard Quality Detection for Real-Time Based on QD-YOLO |
| title_short | Algorithm of Computer Mainboard Quality Detection for Real-Time Based on QD-YOLO |
| title_sort | algorithm of computer mainboard quality detection for real time based on qd yolo |
| topic | deep learning YOLO composite attention computer mainboard quality detection real-time detection |
| url | https://www.mdpi.com/2079-9292/11/15/2424 |
| work_keys_str_mv | AT guangmingtu algorithmofcomputermainboardqualitydetectionforrealtimebasedonqdyolo AT jiaohuaqin algorithmofcomputermainboardqualitydetectionforrealtimebasedonqdyolo AT nealnxiong algorithmofcomputermainboardqualitydetectionforrealtimebasedonqdyolo |