eLibrary
  • Home
  • Sources
  • Search
  • About

Research on a YOLOv8-Based Metal Residue Detection Algorithm

Qingqi He, Siyuan Zhao, Yunlong Liu, Yongxing Li, Yi Yang, Fangfang Hou
Academic Journal of Applied Sciences, (2026), Vol.2, No.1, pp.50-54
Published: June 12, 2026
DOI: 10.54097/d3r2cg88
PDF: Download Full Text PDF
Abstract

To address the recognition challenges caused by the tiny size of metal residues, high reflectivity, and severe background texture interference in industrial production environments, this paper proposes a YOLOv8-based metal residue recognition algorithm. First, to overcome the scarcity of high-quality samples in industrial sites, a metal residue dataset containing multiple complex backgrounds such as welds and oil stains is constructed by simulating actual working conditions. Targeted data augmentation techniques are employed to enhance the model's generalization ability in extreme environments. Second, to tackle the problems of extremely low pixel occupancy of metal targets and the difficulty of feature extraction, a lightweight coordinate attention mechanism is introduced into the backbone network. By capturing cross-channel directional and positional information, the model's perception and extraction capabilities of subtle metal edge features are strengthened. Experimental results show that the improved algorithm achieves a mean average precision (mAP) of 0.724 on the self-built dataset. While maintaining real-time inference speed, it can accurately identify metallic foreign objects with extremely small diameters, effectively reducing the miss rate and false alarm rate under complex working conditions, thus providing reliable technical support for the deployment of industrial precision inspection and automated rejection systems.

Keywords: Metal Residue Recognition, YOLOv8, Small Object Detection, Deep Learning, Feature Fusion
APA Citation: Qingqi He, Siyuan Zhao, Yunlong Liu, Yongxing Li, Yi Yang, Fangfang Hou (2026). Research on a YOLOv8-Based Metal Residue Detection Algorithm. Academic Journal of Applied Sciences, 2(1), 50-54. https://doi.org/10.54097/d3r2cg88

References

  1. Zhang, Z., Zhang, J., Chen, Q., et al. (2026). Unification of closed-open industrial detection scenarios: New large-scale benchmarks, challenges and baselines. IEEE Transactions on Pattern Analysis and Machine Intelligence. https://doi.org/10.1109/TPAMI.2026.3680569
  2. Duan, G., Pan, X., Wang, D., et al. (2026). Surface defect detection of mosaic ceramic walls based on deep learning. Journal of Computing in Civil Engineering, 40(5). https://doi.org/10.1061/JCCEE5.CPENG-7309
  3. Chen, W., Deng, Q., Xiang, Z., et al. (2026). FDAYOLOv8: refined small object detection in unmanned aerial vehicle imagery. Scientific Reports. https://doi.org/10.1038/s41598-026-51902-3
  4. Gupta, V., & Mangal, D. (2026). A deep learning approach based small object detection for dynamic digital twins in smart manufacturing. Computers & Electrical Engineering, 136, 111246. https://doi.org/10.1016/j.compeleceng.2026.111246
  5. Zhang, W., Du, Y., & Wu, Z. (2026). Helmet-wearing detection with small object recognition via improved YOLOv8 in complex environments. Digital Signal Processing, 176, 106066. https://doi.org/10.1016/j.dsp.2026.106066
  6. Yang, W., Zhang, B., Guo, S., et al. (2026). Small target detection of floating objects in river channels based on improved YOLOv7. Scientific Reports, 16(1), 11423. https://doi.org/10.1038/s41598-026-40688-z
  7. Hu, P., Dong, L. (2023). A multi-scale pyramid feature fusion-based object detection method for remote sensing images. International Journal of Remote Sensing, 44(24), 7790–7807. https://doi.org/10.1080/01431161.2023.2288947
  8. Ma, J., Ge, S., Dong, Y., et al. (2023). Instance segmentation algorithm based on fine-grained feature perception and cross-path aggregation. Knowledge-Based Systems, 276. https://doi.org/10.1016/j.knosys.2023.110754
  9. Macías, C. M. F., Maldonado, S. J. F., Álvarez, M. P., et al. (2026). Torchmil: A PyTorch-based library for deep multiple instance learning. Neurocomputing, 680, 133286. https://doi.org/10.1016/j.neucom.2026.133286
  10. Ling, J., Wu, H., & Peng, J. (2026). Bio-inspired small object motion detection visual network based on motion and local entropy information. Engineering Applications of Artificial Intelligence, 177, 114877. https://doi.org/10.1016/j.engappai.2026.114877
  11. Raj, E. C. E., & Shaji, S. R. (2026). Energy Harvesting in Mobile Networks: A Microstrip Circular Patch Antenna Design for Efficient Radio Frequency Signal Capture. International Journal of Communication Systems, 39(9), e70502. https://doi.org/10.1002/dac.70502
  12. Tian, H. (2025). A comprehensive review of YOLO object detection algorithms. Electronics Science Technology and Application, 12(2). https://doi.org/10.59429/esta.v12i2.10579
  13. Muhammad, S., & Guo, Z. (2022). Deep Residual Learning for Image Recognition: A Survey. Applied Sciences, 12(18), 8972. https://doi.org/10.3390/app12188972
  14. Wu, S., Kong, H., & Xu, Z. (2026). HYOLO: A lightweight and efficient detection framework for small objects in aerial images. Expert Systems with Applications, 328, 132794. https://doi.org/10.1016/j.eswa.2026.132794
  15. Zeng, W. (2024). Image data augmentation techniques based on deep learning: A survey. Mathematical Biosciences and Engineering, 21(6), 6190–6224. https://doi.org/10.3934/mbe.2024272
© 2026 eLibrary · Stand on the shoulders of giants