Machine Vision-Based Defect Detection for Automotive Brake Pads: A Review of System Components, Image Processing Methods, and Applications
DOI:
https://doi.org/10.63808/aepm.v2i4.443Keywords:
Automotive brake pads, Machine vision, Defect detection, Image processing, Deep learningAbstract
Automotive brake pads are safety-critical components whose manufacturing quality directly affects braking reliability. Manual inspection is inefficient and susceptible to subjective judgment, whereas machine vision provides a non-contact and automated solution for defect detection. This article reviews machine vision-based inspection of automotive brake pads from three perspectives: system components, image processing methods, and industrial applications. The reviewed technologies include image acquisition hardware, conventional image processing, machine learning, deep learning, and their applications to contour, surface, character, and dimensional inspection. Existing methods are compared in terms of detection capability, interpretability, data dependence, computational cost, environmental robustness, and deployment suitability.The literature shows that conventional image processing remains effective under stable imaging conditions, while deep learning offers stronger feature representation and adaptability but requires representative datasets and greater computing resources. Current challenges include limited public datasets, inconsistent evaluation protocols, sensitivity to industrial variations, and the trade-off between accuracy and real-time performance. Future research should emphasize standardized datasets, lightweight models, few-shot learning, multimodal sensing, and integration with intelligent manufacturing systems. This review provides a reference for the development and industrial deployment of machine vision-based brake-pad inspection.
References
[1] Zhao, L., Huang, W., & Sun, Z. (2018). A color segmentation and feature matching algorithm for car brake pad image classification. In Proceedings of the International Conference on Machine Vision and Applications (pp. 8–12).
[2] Gnanasekaran, S., Jakkamputi, L. P., Rakkiyannan, J., Thangamuthu, M., & Bhalerao, Y. (2023). A comprehensive approach for detecting brake pad defects using histogram and wavelet features with nested dichotomy family classifiers. Sensors, 23(22), Article 9093. https://doi.org/10.3390/s23229093
[3] Zhao, H., & Wang, T. (2024). Surface wear detection of automotive cermet composite brake pads based on machine vision. International Journal of Microstructure and Materials Properties, 17(2–3), 151–170.
[4] Zhang, T., Liu, Y., Yang, Y., & Jin, Y. (2020). Research on brake pad surface defects detection based on deep learning. In 2020 39th Chinese Control Conference (CCC) (pp. 7310–7315). IEEE. https://doi.org/10.23919/CCC50068.2020.9188622
[5] Cong, Z., Li, X., & Huang, Z. (2023). Research on brake pad surface defect detection method based on deep learning. In 2023 International Conference on Advances in Electrical Engineering and Computer Applications (AEECA) (pp. 813–818). IEEE. https://doi.org/10.1109/AEECA59782.2023.00000
[6] Guo, J., Yang, Y., Xiong, X., Yang, Y., & Shao, M. (2024). Brake disc positioning and defect detection method based on improved Canny operator. IET Image Processing, 18(5), 1283–1295. https://doi.org/10.1049/ipr2.13022
[7] Wei, Y., & Yin, J. (2025). Defect detection in disc brake pads using an improved AlexNet convolutional neural network. International Journal of Automotive and Mechanical Engineering, 22(3), 12654–12664.
[8] Zhang, H.-D., & Yuan, X. (2021). Image self-generation based defect detection method for train brake pad. In 2021 China Automation Congress (CAC) (pp. 3707–3712). IEEE. https://doi.org/10.1109/CAC53003.2021.9727842
[9] Chang, Y., Li, R., Ma, D., Ma, X., & Song, D. (2023). Thickness measurement of brake pads based on keypoint and object detection. In 2023 IEEE International Conference on Unmanned Systems (ICUS) (pp. 104–109). IEEE. https://doi.org/10.1109/ICUS58632.2023.10318372
[10] Guo, Y., Zhang, X., & Dong, Z. (2024). Car brake disc surface defect detection based on improved YOLOv5. IEEE Access, 12, 68601–68610. https://doi.org/10.1109/ACCESS.2024.3399667
[11] Bin, Z., Cong, W., & Xue, L. (2022). Research on surface defect detection system of brake disc. In 2022 IEEE 5th Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC) (Vol. 5, pp. 630–634). IEEE. https://doi.org/10.1109/IMCEC55388.2022.10019982
[12] Feng, L., Yu, Z., Juan, G., & An, Q. (2024). Surface defect detection of brake discs based on the IGD-IHT algorithm and the PIQEDS-IBPSO-NESN algorithm. Instrumentation, 11(3), 62–73.
[13] Dózsa, T., Őri, P., Szabari, M., Simonyi, E., Soumelidis, A., & Lakatos, I. (2024). Brake disc deformation detection using intuitive feature extraction and machine learning. Machines, 12(4), Article 214. https://doi.org/10.3390/machines12040214
[14] Lee, J., Woo, U., Lee, M.-H., Kim, J.-Y., Choi, H., & Oh, T. (2025). Real-time defect identification in automotive brake calipers using PCA-optimized feature extraction and machine learning. Sensors, 25(21), Article 6753. https://doi.org/10.3390/s25216753
[15] Chen, Y., Ding, Y., Zhao, F., Zhang, E., Wu, Z., & Shao, L. (2021). Surface defect detection methods for industrial products: A review. Applied Sciences, 11(16), Article 7657. https://doi.org/10.3390/app11167657
[16] Yang, J., Li, S., Wang, Z., Dong, H., Wang, J., & Tang, S. (2020). Using deep learning to detect defects in manufacturing: A comprehensive survey and current challenges. Materials, 13(24), Article 5755. https://doi.org/10.3390/ma13245755
[17] Zheng, X., Zheng, S., Kong, Y., & Chen, J. (2021). Recent advances in surface defect inspection of industrial products using deep learning techniques. The International Journal of Advanced Manufacturing Technology, 113(1), 35–58. https://doi.org/10.1007/s00170-021-08504-2
[18] Liu, Y., Zhang, C., & Dong, X. (2023). A survey of real-time surface defect inspection methods based on deep learning. Artificial Intelligence Review, 56(10), Article 12131. https://doi.org/10.1007/s10462-023-10534-1
[19] Steger, C., Ulrich, M., & Wiedemann, C. (2018). Machine vision algorithms and applications. John Wiley & Sons.
[20] Ren, Z., Fang, F., Yan, N., & Wu, Y. (2022). State of the art in defect detection based on machine vision. International Journal of Precision Engineering and Manufacturing-Green Technology, 9(2), 661–691. https://doi.org/10.1007/s40684-021-00348-z
[21] Engelberg, J., & Levy, U. (2022). Generalized metric for broadband flat lens performance comparison. Nanophotonics, 11(16), 3559–3574. https://doi.org/10.1515/nanoph-2022-0137
[22] Mendis, S., Kemeny, S. E., & Fossum, E. R. (2002). CMOS active pixel image sensor. IEEE Transactions on Electron Devices, 41(3), 452–453. https://doi.org/10.1109/16.275225
[23] Bhatt, P. M., Malhan, R. K., Rajendran, P., Shah, B. C., Thakar, S., Yoon, Y. J., & Gupta, S. K. (2021). Image-based surface defect detection using deep learning: A review. Journal of Computing and Information Science in Engineering, 21(4), Article 040801. https://doi.org/10.1115/1.4049535
[24] Tabernik, D., Šela, S., Skvarč, J., & Skočaj, D. (2020). Segmentation-based deep-learning approach for surface-defect detection. Journal of Intelligent Manufacturing, 31(3), 759–776. https://doi.org/10.1007/s10845-019-01476-x
[25] Zhao, L., Zhang, W., Sun, Z., & Chen, Q. (2018). Brake pad image classification algorithm based on color segmentation and information entropy weighted feature matching. Journal of Tsinghua University (Science and Technology), 58(6), 547–552. https://doi.org/10.16511/j.cnki.qhdxxb.2018.22.018
[26] Li, Z. (2022). Wear detection of carbon fibre composite automobile brake pads based on bilateral filtering. International Journal of Microstructure and Materials Properties, 16(2–3), 217–227. https://doi.org/10.1504/IJMMP.2022.125566
[27] Canny, J. (1986). A computational approach to edge detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, PAMI-8(6), 679–698. https://doi.org/10.1109/TPAMI.1986.4767851
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Hao Teng, Haorong Wu, Qiurong Lv, Xiaoxiao Li
This work is licensed under a Creative Commons Attribution 4.0 International License.