Metal Surface Defect Detection Method Based on Machine Vision

Yibo Wang; Xiaoduo Yang; Yaojun Yu

doi:10.54097/7tymd878

Authors

Yibo Wang
Xiaoduo Yang
Yaojun Yu

DOI:

https://doi.org/10.54097/7tymd878

Keywords:

Metal surface defect, Imaging technology, feature fusion, attention mechanism.

Abstract

Metal material is the core part of the strategic industrial fields such as aerospace, automobile manufacturing, precision electronics, energy equipment and so on. Its performance will determine the performance and reliability of industrial products. With the development of the times, the requirements for metal parts in industrial and other fields tend to be refined, complicated and slightly flawed, which may lead to chain problems such as performance degradation and sudden loss of life, and may even lead to safety accidents. In this context, the defect detection of metal surface will become an indispensable part of the future industrial intelligent production from the auxiliary link in traditional production. Based on this development status, this paper systematically studies the Chinese and English literature in the field of metal surface defect detection in recent years. Through a lot of reading, this paper not only summarizes the common defect types of metals, but also introduces the image processing and feature extraction in detail, and puts forward the relevant metal surface defect detection methods. The research results can not only provide reference for relevant enterprises, but also inspire subsequent researchers, and have a wide range of applications and academic inspiration.

References

[1] Wu Lin, Hao Hongyu, Song You. A review of industrial metal surface defect detection based on computer vision. Acta Automatica Sinica, 2024, 50 (07): 1261 - 1283.

[2] Lu Hongtao, Zhang Qinchuan. A review of research on the application of deep convolutional neural networks in computer vision. Data Acquisition and Processing, 2016, 31 (01): 1 - 17.

[3] Zhang Shun, Gong Yihong, Wang Jinjun. Development of deep convolutional neural networks and their application in the field of computer vision. Chinese Journal of Computers, 2019, 42 (03): 453 - 482.

[4] Li Song, Zhou Yatong, Zhang Zhongwei, Chi Yue, Han Chunying. Surface defect detection of stamped parts based on dual-light template matching. Forging Technology, 2018, 43 (11): 137 − 145.

[5] Chan Y, et al. FOHR Net: Metal surface defect detection network for high-speed steel strip environments. Scientific Reports, 2024.

[6] Aloha Airlines Flight 243. Wikipedia, 2025 - 10 - 07.

[7] Zerbst U, et al. Defects as a root cause of fatigue failure of metallic components III – Cavities, dents, corrosion pits, scratches. Engineering Failure Analysis, Elsevier, 2019.

[8] Smith B. Geometrical shadowing of a random rough surface. IEEE Transactions on Antennas and Propagation, 1967, 15 (5): 668 − 671.

[9] Foucher B. Infrared machine vision: A new contender. In: Proceedings of the SPIE 3700, Thermosense XXI. Orlando, USA: SPIE, 1999: 210 − 213.

[10] Nayar S K, Ikeuchi K, Kanade T. Surface reflection: Physical and geometrical perspectives. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1991, 13 (7): 611 − 634.

[11] Wang Yu, Wu Zhiheng, Deng Zhiwen, et al. Surface defect detection system for metal parts based on machine vision. Mechanical Engineering and Automation, 2018, (04): 210 - 211+214.

[12] Zhang Xuewu, Ding Yanqiong, Yan Ping. A visual detection method for surface defects of strongly reflective metals based on infrared imaging. Acta Optica Sinica, 2011, 31 (03): 112 - 120.

[13] Zhang Yanling, Liu Guixiong, Cao Dong, et al. Basic algorithms of mathematical morphology and their application in image preprocessing. Science Technology and Engineering, 2007, (03): 356 - 359.

[14] Huang Y, Yu T, Wan K, Yuan J. Detection and Classification of Metal Workpiece Surface Defects Based on Machine Vision. 2021 IEEE International Conference on Advances in Electrical Engineering and Computer Applications (AEECA), Dalian, China, 2021: 983 - 987.

[15] Ahmad I, Moon, Shin S J. Color-to-grayscale algorithms effect on edge detection — A comparative study. 2018 International Conference on Electronics, Information, and Communication (ICEIC), Honolulu, HI, USA, 2018: 1 - 4.

[16] Ishak M H, Mohd Marzuki N S, Abdullah M F, Che Soh Z H, Isa I S, Sulaiman S N. Image Quality Assessment for Image Filtering Algorithm: Qualitative and Quantitative Analyses. 2019 9th IEEE International Conference on Control System, Computing and Engineering (ICCSCE), Penang, Malaysia, 2019: 162 - 167.

[17] Tsay H-L, Lin C-H, Chen M-F, Lin P-M, Lien C-C, Kuo H-J. Radiometric and Geometric Correction Methods for SWIR Cameras. 2022 25th International Conference on Mechatronics Technology (ICMT), Kaohsiung, Taiwan, 2022: 1 - 5.

[18] Huang M, Yang T, Fu C, Fan X. Target Recognition Based on Improved Fourier Descriptors. 2022 China Automation Congress (CAC), Xiamen, China, 2022: 2780 - 2784.

[19] Yin Y, Meng Z, Li S. Feature extraction and image recognition for the electrical symbols based on Zernike moment. 2017 IEEE 2nd Advanced Information Technology, Electronic and Automation Control Conference (IAEAC), Chongqing, China, 2017: 1031 - 1035.

[20] Gashnikov M. Preprocessing for Geometric Matching of Digital Images. 2024 X International Conference on Information Technology and Nanotechnology (ITNT), Samara, Russian Federation, 2024: 1 - 4.

[21] Qiu L, Qin W, Yang H, Chen Y. HRNet: Local-Spatial Feature Fusion Network for Texture Recognition. 2024 Asia-Pacific Conference on Image Processing, Electronics and Computers (IPEC), Dalian, China, 2024: 535 - 540.

[22] Liang X, Xu L. Research on Dynamic Weight Feature Extraction Based on Gray-Level Distribution. 2024 IEEE 7th International Conference on Information Systems and Computer Aided Education (ICISCAE), Dalian, China, 2024: 858 - 865.

[23] Hütten N, Alves Gomes M, Hölken F, Andricevic K, Meyes R, Meisen T. Deep learning for automated visual inspection in manufacturing and maintenance: a survey of open-access papers. Applied System Innovation, 2024, 7 (1): 11.

[24] Wen X, Shan J, He Y, Song K. Steel surface defect recognition: A survey. Coatings, 2022, 13 (1): 17.

[25] Ameri R, Hsu C, Band S. A systematic review of deep learning approaches for surface defect detection in industrial applications. Engineering Applications of Artificial Intelligence, 2024, 130: 107717.

[26] Frydrych K, Tomczak M, Jasiński J, Papanikolaou S. Steel surface defects analysis with machine vision and deep learning. The International Journal of Advanced Manufacturing Technology, 2025, 140 (7): 3691 - 3710.

[27] Liu L, Ouyang W, Wang X, Fieguth P, Chen J, Liu X, Pietikäinen M. Deep learning for generic object detection: A survey. International Journal of Computer Vision, 2020, 128 (2): 261 - 318.

[28] Terven J, Córdova-Esparza D M, Romero-González J A. A comprehensive review of YOLO architectures in computer vision: From YOLOv1 to YOLOv8 and YOLO-NAS. Machine Learning and Knowledge Extraction, 2023, 5 (4): 1680 - 1716.

[29] Lin T Y, Dollár P, Girshick R, He K, Hariharan B, Belongie S. Feature pyramid networks for object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 2117 - 2125.

[30] Yu S, Liu Z, Zhang L, Zhang X, Wang J. FasterNet-YOLO for real-time detection of steel surface defects algorithm. PLoS One, 2025, 20 (5): e0323248.

[31] Wei C, Bao Y, Zheng C, Ji Z. AMFNet: Aggregated multi-level feature interaction fusion network for defect detection on steel surfaces. Journal of Intelligent Manufacturing, 2025: 1 - 18.

[32] Zhou C, Lu Z, Lv Z, et al. Metal surface defect detection based on improved YOLOv5. Scientific Reports, 2023, 13: 20803.