A Review of Surface Defect Detection Technologies Based on Machine Vision
Main Article Content
Keywords
surface defect detection, machine vision, machine learning, deep learning, few-shot learning
Abstract
Machine vision-based surface defect detection offers the advantages of being non-contact, non-destructive, and highly automated; consequently, it is widely applied across various industrial production processes. This article provides a brief overview of commonly used methods for surface defect detection, evaluation indicators for detection results, and key challenges currently faced. Defect detection methods are categorized into three types: traditional image processing methods, traditional machine learning methods, and deep learning methods. The core principles and representative studies of each method are reviewed, and their respective advantages and limitations are analyzed. We briefly describe the method for evaluating detection results, examine the few-shot learning problem encountered in practical applications, and provide an outlook on feasible pathways for addressing this issue in the future.
References
- [1] Yang, Z. Q., Zhang, M. X., Chen, Y. S., et al. (2023). Research progress on surface defect detection methods based on machine vision. Modern Manufacturing Engineering, (4), 143–156. https://doi.org/10.16731/j.cnki.1671-3133.2023.04.020
- [2] Zhao, J. A. (2016). Research on theories and methods for workpiece surface defect detection based on image processing (Master's thesis, Southeast University).
- [3] Han, J. Y., Cao, J. T., Wang, H. N., et al. (2022). A review of fabric defect detection methods based on computer vision. Journal of Liaoning Petrochemical University, 42(1), 70–77.
- [4] Yang, J. F., Qiao, P. R., Li, Y. M., et al. (2019). A review of machine learning classification problems and algorithms. Statistics & Decision, 35(6), 36–40. https://doi.org/10.13546/j.cnki.tjyjc.2019.06.008
- [5] Wei, R., & Bi, Y. (2019). Research on recognition technology of aluminum profile surface defects based on deep learning. Materials, 12(10), 1–14.
- [6] Girshick, R., Donahue, J., Darrell, T., et al. (2015). Region-based convolutional networks for accurate object detection and segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 38(1), 142–158.
- [7] Redmon, J., Divvala, S., Girshick, R., et al. (2016). You only look once: Unified, real-time object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 779–788). IEEE.
- [8] Liu, W., Anguelov, D., Erhan, D., et al. (2016). SSD: Single shot multibox detector. In B. Leibe, J. Matas, N. Sebe, & M. Welling (Eds.), Computer Vision – ECCV 2016 (pp. 21–37). Springer.
- [9] Dai, J., Li, Y., He, K., et al. (2016). R-FCN: Object detection via region-based fully convolutional networks. In Advances in Neural Information Processing Systems 29 (NIPS 2016) (pp. 379–387). Curran Associates, Inc.
- [10] Li, J., Su, Z., Geng, J., et al. (2018). Real-time detection of steel strip surface defects based on an improved YOLO detection network. IFAC-PapersOnLine, 51(21), 76–81.
- [11] Xue, Y., & Li, Y. (2018). A fast detection method via region-based fully convolutional neural networks for shield tunnel lining defects. Computer-Aided Civil and Infrastructure Engineering, 33(8), 638–654.
Article Sidebar
This work is licensed under a Creative Commons Attribution 4.0 International License.