Scopus

A Lightweight Hybrid Approach for Surface Defect Detection in Industrial RAW Images Using HOG and SVM

Năm XB 2026 Tạp chí / Hội thảo Advances in Information and Communication Technology: Proceedings of the 4th International Conference, ICTA 2025, Volume 1 Volume 1, pp. 123-133 Đơn vị ICTU DOI / Link https://link.springer.com/chapter/10.1007/978-3-032-18316-3_15 ↗

Tác giả

Thi Canh Hoang

Tóm tắt

Surface defect detection is crucial for ensuring high quality and minimizing defects in industrial products. This paper proposes a lightweight hybrid approach for detecting surface defects in industrial RAW images, optimized for quality control. The method combines traditional image processing techniques such as contrast enhancement, differential imaging, and morphological operations with Histogram of Oriented Gradients feature extraction and Support Vector Machine classification. Experimental evaluations on real-world datasets report strong robustness and practical effectiveness.

Tài liệu tham khảo

[1] Ling, Q., Isa, N.A.M.: Printed circuit board defect detection methods based on image processing, machine learning and deep learning: a survey. IEEE Access 11, 15921–15944 (2023)

[2] Cheng, Y., Wang, Y., Lin, J., Xu, S., Zhang, P.: Research status of the influence of machining processes and surface modification technology on the surface integrity of bearing steel materials. Int. J. Adv. Manuf. Technol. 125(7), 2897–2923 (2023)

[3] Szeliski, R.: Computer vision: algorithms and applications. Springer Nature (2022)

[4] Tang, B., Chen, L., Sun, W., Lin, Z.K.: Review of surface defect detection of steel products based on machine vision. IET Image Proc. 17(2), 303–322 (2023)

[5] Zheng, X., Zheng, S., Kong, Y., Chen, J.: Recent advances in surface defect inspection of industrial products using deep learning techniques. Int. J. Adv. Manuf. Technol. 113, 35–58 (2021)

[6] Tsai, D.M., Molina, D.E.R.: Morphology-based defect detection in machined surfaces with circular tool-mark patterns. Measurement 134, 209–217 (2019)

[7] An, H., et al.: HOG-PCA-Block-Voting: lighter and smaller but faster. Proc. 2024 2nd Int. Conf. Mechatronics, IoT and Industrial Informatics (ICMIII), pp. 786–793, IEEE (2024)

[8] Mao, T., et al.: Defect recognition method based on HOG and SVM for drone inspection images of power transmission line. In: 2019 international conference on high performance big data and intelligent systems (HPBD&IS), pp. 254–257, IEEE (2019)

[9] Chen, Z., Feng, X., Liu, L., Jia, Z.: Surface defect detection of industrial components based on vision. Sci. Rep. 13(1), 22136 (2023)

[10] Xu, X., Li, X.: Research on surface defect detection algorithm of pipeline weld based on YOLOv7. Sci. Rep. 14(1), 1881 (2024)

[11] Xia, B., Cao, J., Wang, C.: SSIM-NET: Real-time PCB defect detection based on SSIM and MobileNet-V3. In: 2019 2nd World conference on mechanical engineering and intelligent manufacturing (WCMEIM), pp. 756–759. IEEE (2019)

[12] Zhang, D., et al.: An efficient lightweight convolutional neural network for industrial surface defect detection. Artif. Intell. Rev. 56(9), 10651–10677 (2023)

[13] Kong, Q., Wu, Z., Song, Y.: Online detection of external thread surface defects based on an improved template matching algorithm. Measurement 195, 111087 (2022)

Ghi chú

Source ID: 74; Author classification: ICTU - Main Author; First listed author: Van Son Nguyen; Contact author: Hoang Thi Canh; Total authors: 5; Springer matched from provided ICTA 2025 volumes

← Quay lại danh sách bài báo