Improved YOLOv11n-Based Algorithm for Wood Surface Defect Detection with Edge-Guided and Adaptive Fusion Modules

Jifa Li

doi:10.63313/AJET.9058

Authors

Jifa Li Tianjin University of Technology and Education, Tianjin, 300222, China Author

DOI:

https://doi.org/10.63313/AJET.9058

Keywords:

WLA-YOLO, YOLOv11n, Wood Surface Defect Detection, Edge-Guided P2 Branch, Local-Context Attention, Adaptive Feature Fusion

Abstract

Wood surface defect detection is a critical process in industrial quality control. This manuscript proposes WLA-YOLO, an estimated YOLOv11n improvement that integrates an Edge-Guided P2 Branch, Grain-aware Local-Context Attention, and Adaptive Fusion FPN. The method is designed to improve fine crack localization, suppress wood-grain interference, and balance multi-scale feature fusion.t WLA-YOLO reach 75.1% [email protected] and 39.8% [email protected]:0.95 on an 7-class wood surface defect dataset.

References

[1] Jocher, G., & Qiu, J. (2024). Ultralytics YOLO11 (Version 11.0.0) [Computer software]. https://github.com/ultralytics/ultralytics

[2] Luo, H., Cai, L., & Li, C. (2023). Rail surface defect detection based on an improved YOLOv5s. Applied Sciences, 13(12), 7330. https://doi.org/10.3390/app13127330

[3] Zhang, C., Xu, D., Zhang, L., & Deng, W. (2023). Rail surface defect detection based on image enhancement and improved YOLOX. Electronics, 12(12), 2672. https://doi.org/10.3390/electronics12122672

[4] Wang, Y., Zhang, K., Wang, L., & Wu, L. (2024). An improved YOLOv8 algorithm for rail surface defect detection. IEEE Access, 12, 44984-44997. https://doi.org/10.1109/ACCESS.2024.3380009

[5] Du, J., Zhang, R., Gao, R., Nan, L., & Bao, Y. (2024). RSDNet: A new multiscale rail surface defect detection model. Sensors, 24(11), 3579. https://doi.org/10.3390/s24113579

[6] Park, K. B., & Lee, J. Y. (2022). Novel industrial surface-defect detection using deep nested convolutional network with attention and guidance modules. Journal of Computational Design and Engineering, 9(6), 2466-2481.

[7] Gao, L., Zhang, J., Yang, C., & Zhou, Y. (2022). Cas-VSwin transformer: A variant swin transformer for surface-defect detection. Computers in Industry, 140, 103689.

[8] Wang, A., Chen, H., Liu, L., Chen, K., Lin, Z., Han, J., & Ding, G. (2024). YOLOv10: Real-time end-to-end object detection. Advances in Neural Information Processing Systems, 37.