PBD-YOLO: Dual-Strategy Integration of Multi-Scale Feature Fusion and Weak Texture Enhancement for Lightweight Particleboard Surface Defect Detection
Source abstract
Abstract
Surface defect detection plays an important role in particleboard quality control. But it still faces challenges in detecting coexisting multi-scale defects and weak texture defects. To address these issues, this study proposed PBD-YOLO (Particleboard Defect-You Only Look Once), a lightweight YOLO-based algorithm with multi-scale feature fusion and weak texture enhancement capabilities. In order to improve the ability of the algorithm to extract weak texture features, the SPDDEConv (Space to Depth and Difference Enhance Convolution) module was introduced in this study, which reduced the loss of information in the down-sampling process through space-to-depth transformation and enhanced the edge information of weak texture defects through difference convolution. This approach improved the mAP (mean average precision) of weakly featured but edge-sensitive defects (such as scratches) by as much as 20.9%. In order to improve the algorithm’s ability to detect multi-scale defects, this study introduced the ShareSepHead (Share Separated Head) and C2f_SAC (C2f module with Switchable Atrous Convolution) modules. ShareSepHead fused feature maps from different scales of the neck network by adding a convolutional layer with shared weights, and the C2f_SAC module adaptively fused multi-rate receptive fields through a switching mechanism. The synergistic effect of ShareSepHead and C2f_SAC improved the detection accuracy of multi-scale defects by 10.6–20.8%. The experimental results demonstrated that PBD-YOLO achieved 85.6% mAP at 50% intersection over union (IoU) and 81.4% recall, surpassing YOLOv10 by 5.5% and 13%, respectively, while reducing parameters by 11.3%. In summary, it could be better to meet the need of accurately detecting surface defects on particleboard.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Industrial Vision Systems and Defect Detection · Advanced Neural Network Applications · Image and Object Detection Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Research Institute of Wood Industry, Chinese Academy of Forestry, Beijing 100091, China
School of Instrumentation Science and Engineering, Harbin Institute of Technology, Harbin 150006, China
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China
School of Technology, Beijing Forestry University, Beijing 100083, China
Funding
National Key R&D Program of China
References (40)
Show source-provided references
1. Review and Outlook of Technology Development in China’s Particleboard Industry
2. A Brief Analysis of China’s Artificial Board Industry
3. Application of Machine Vision in Particleboard Surface Defect Detection:Status and Recommendations
4. Development of Intelligent Control and Testing of Particleboard Quality
5. Zhao, Z., Ge, Z., Jia, M., Yang, X., Ding, R., and Zhou, Y. (2022). A Particleboard Surface Defect Detection Method Research Based on the Deep Learning Algorithm. Sensors, 22.10.3390/s22207733 ↗
6. Li, B., Xu, Z., Bian, E., Yu, C., Gao, F., and Cao, Y. (2022, January 1–3). Particleboard Surface Defect Inspection Based on Data Augmentation and Attention Mechanisms. Proceedings of the 2022 27th International Conference on Automation and Computing (ICAC), Bristol, UK.10.1109/ICAC55051.2022.9911064 ↗
7. Wang, C., Liu, Y., and Wang, P. (2019). Extraction and Detection of Surface Defects in Particleboards by Tracking Moving Targets. Algorithms, 12.10.3390/a12010006 ↗
8. Detection Model of Wood Surface Defects Based on Improved YOLOv5s
9. Zhang, Y., Li, X., Wang, F., Wei, B., and Li, L. (2021, January 17–20). A Comprehensive Review of One-Stage Networks for Object Detection. Proceedings of the 2021 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC), Xi’an, China.10.1109/ICSPCC52875.2021.9564613 ↗
10. Zhang, H., Wang, Y., and Yu, C. (2021, January 27–29). Research on Key Technology of Online Detection for Particleboard. Proceedings of the 2021 IEEE International Conference on Electronic Technology, Communication and Information (ICETCI), Changchun, China.10.1109/ICETCI53161.2021.9563486 ↗
11. Zhao, Z., Yang, X., Zhou, Y., Sun, Q., Ge, Z., and Liu, D. (2021). Real-Time Detection of Particleboard Surface Defects Based on Improved YOLOV5 Target Detection. Sci. Rep., 11.10.1038/s41598-021-01084-x ↗
12. Detecting Method for Particleboard Surface Defects Based on the Lite-YOLOv5s Model
13. Wang, C., Liu, Y., Wang, P., and Lv, Y. (2023). Research on the Identification of Particleboard Surface Defects Based on Improved Capsule Network Model. Forests, 14.10.3390/f14040822 ↗
14. Small Defect Detection Algorithm of Particle Board Surface Based on Improved YOLOv5s
15. Surface defect detection method of particleboard based on improved YOLOv5s model
16. Mehta, S., and Rastegari, M. (2021, January 6). MobileViT: Light-Weight, General-Purpose, and Mobile-Friendly Vision Transformer. Proceedings of the International Conference on Learning Representations (ICLR), Virtually.
17. LE–MSFE–DDNet: A Defect Detection Network Based on Low-Light Enhancement and Multi-Scale Feature Extraction10.1007/s00371-021-02210-6 ↗
18. Enriched Multi-Scale Cascade Pyramid Features and Guided Context Attention Network for Industrial Surface Defect Detection10.1016/j.engappai.2023.106369 ↗
19. EMRA-Net: A Pixel-Wise Network Fusing Local and Global Features for Tiny and Low-Contrast Surface Defect Detection10.1109/TIM.2022.3151926 ↗
20. Pu, M., Huang, Y., Liu, Y., Guan, Q., and Ling, H. (2022, January 18–24). EDTER: Edge Detection with Transformer. Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.10.1109/CVPR52688.2022.00146 ↗
21. Amini, M.-R., Canu, S., Fischer, A., Guns, T., Kralj Novak, P., and Tsoumakas, G. (2022, January 19–23). No More Strided Convolutions or Pooling: A New CNN Building Block for Low-Resolution Images and Small Objects. Proceedings of the Machine Learning and Knowledge Discovery in Databases, Grenoble, France.
22. DEA-Net: Single Image Dehazing Based on Detail-Enhanced Convolution and Content-Guided Attention10.1109/TIP.2024.3354108 ↗
23. Akyon, F.C., Onur Altinuc, S., and Temizel, A. (2022, January 6–19). Slicing Aided Hyper Inference and Fine-Tuning for Small Object Detection. Proceedings of the 2022 IEEE International Conference on Image Processing (ICIP), Bordeaux, France.10.1109/ICIP46576.2022.9897990 ↗
24. Deep Long-Tailed Learning: A Survey10.1109/TPAMI.2023.3268118 ↗
25. External Defects of Particleboard and Their Countermeasures
26. Wang, A., Chen, H., Liu, L., Chen, K., Lin, Z., Han, J., and Ding, G. (2024, January 10–15). YOLOv10: Real-Time End-to-End Object Detection. Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024 (NeurIPS 2024), Vancouver, BC, Canada.
27. Understanding the Effective Receptive Field in Deep Convolutional Neural Networks
28. Xie, S., Girshick, R., Dollár, P., Tu, Z., and He, K. (2017, January 21–26). Aggregated Residual Transformations for Deep Neural Networks. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.634 ↗
29. Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection
30. Yu, F., and Koltun, V. (2016, January 2–4). Multi-Scale Context Aggregation by Dilated Convolutions. Proceedings of the 4th International Conference on Learning Representations (ICLR), San Juan, Puerto Rico.
31. Qiao, S., Chen, L.-C., and Yuille, A. (2021, January 20–25). DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution. Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.10.1109/CVPR46437.2021.01008 ↗
32. Fu, J., Zheng, H., and Mei, T. (2017, January 21–26). Look Closer to See Better: Recurrent Attention Convolutional Neural Network for Fine-Grained Image Recognition. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.476 ↗
33. Lightweight Detection of Ceramic Tile Surface Defects on Improved YOLOv8
34. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks10.1109/TPAMI.2016.2577031 ↗
35. Lyu, C., Zhang, W., Huang, H., Zhou, Y., Wang, Y., Liu, Y., Zhang, S., and Chen, K. (2022). RTMDet: An Empirical Study of Designing Real-Time Object Detectors. arXiv.
36. Zhao, Y., Lv, W., Xu, S., Wei, J., Wang, G., Dang, Q., Liu, Y., and Chen, J. (2024, January 16–22). DETRs Beat YOLOs on Real-Time Object Detection. Proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR52733.2024.01605 ↗
37. Eigen-CAM: Visual Explanations for Deep Convolutional Neural Networks10.1007/s42979-021-00449-3 ↗
38. A Method of Particleboard Surface Defect Detection and Recognition Based on Deep Learning10.1080/17480272.2024.2323579 ↗
39. Ghiasi, G., Lin, T.-Y., and Le, Q.V. (2019, January 15–20). NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.10.1109/CVPR.2019.00720 ↗
40. Surface Defect Detection Methods for Industrial Products with Imbalanced Samples: A Review of Progress in the 2020s10.1016/j.engappai.2023.107697 ↗