Surface defect detection of curved mosaic ceramics based on improved coupling denoising algorithm
-
Guanping Dong
Assoc. Prof. Dr. Guanping Dong, born in 1986, obtained his PhD degree in South China University of Technology, P. R. China. His research interests include machine vision, image recognition, defect detection, and visual image feature extraction.
,
Xingcheng Pan
Xingcheng Pan, born in 1999, is a Master’s students at the Jingdezhen Ceramic University, Jingdezhen, P. R. China.
Dr. Nanshou Wu, born in 1993, obtained his PhD degree in South China Normal University, P. R. China. His research interests include machine vision, and biophotonic imaging technology.
Dr. Xiangyu Kong, born in 1992, obtained his PhD degree in South China Normal University, P. R. China. He is a teacher of Guangdong Polytechnic of Science and Trade, Guangzhou, P. R. China. His research interests include smart manufacturing, defect detection technology.
Dr. Zixi Wang, born in 1973, is an Associate Researcher in the Department of Mechanical Engineering, Tsinghua University, P. R. China. His research includes magnetic suspension bearing and magnetic drive technology, air floating bearing technology, and sealing technology.
Abstract
Mosaic ceramic murals have been valued as remarkable artistic expressions, with three-dimensional patterns providing a greater significance. The surface quality of these ceramics is crucial to the overall aesthetic of the art. However, the detection of surface defects is difficult because of the unique curved surface structure of curved mosaic ceramics. To solve this problem, this paper proposes a visual detection method for curved mosaic ceramics combining an improved coupled denoising algorithm with an adaptive threshold segmentation algorithm. This overcomes the limitations of conventional single-image enhancement algorithms in machine vision, which cannot effectively process images comprising mixed noise signals. The surface defect images of curved mosaic ceramics are first enhanced by combining an optimized Gaussian filter with an improved Fourier convolution transform. Many steps, including adaptive threshold segmentation and feature screening, are then implemented to quickly identify surface defects in curved mosaic ceramics. Afterwards, experiments are conducted, demonstrating that the proposed method achieves an accuracy of 95 % in detecting bulges, scratches, bruises, and cracks on curved mosaic ceramics. Finally, it is shown that the proposed approach is also applicable to other curved-surface products.
Funding source: Science and Technology Program of Guangzhou City
Award Identifier / Grant number: SL2023A04J01572
Funding source: Guangdong Basic and Applied Basic Research Foundation
Award Identifier / Grant number: 2023A1515110166
Funding source: Science and Technology Program of Jingdezhen City
Award Identifier / Grant number: 2023GY001-13
Funding source: National Key R&D Program of China
Award Identifier / Grant number: 2021YFB4001501
Funding source: the Fund of Science and Technology Research Project of Jiangxi Provincial Department of Education
Award Identifier / Grant number: GJJ2400910
Funding source: National Natural Science Foundation of China
Award Identifier / Grant number: 62461029
About the authors
Assoc. Prof. Dr. Guanping Dong, born in 1986, obtained his PhD degree in South China University of Technology, P. R. China. His research interests include machine vision, image recognition, defect detection, and visual image feature extraction.
Xingcheng Pan, born in 1999, is a Master’s students at the Jingdezhen Ceramic University, Jingdezhen, P. R. China.
Dr. Nanshou Wu, born in 1993, obtained his PhD degree in South China Normal University, P. R. China. His research interests include machine vision, and biophotonic imaging technology.
Dr. Xiangyu Kong, born in 1992, obtained his PhD degree in South China Normal University, P. R. China. He is a teacher of Guangdong Polytechnic of Science and Trade, Guangzhou, P. R. China. His research interests include smart manufacturing, defect detection technology.
Dr. Zixi Wang, born in 1973, is an Associate Researcher in the Department of Mechanical Engineering, Tsinghua University, P. R. China. His research includes magnetic suspension bearing and magnetic drive technology, air floating bearing technology, and sealing technology.
-
Research ethics: Not applicable.
-
Informed consent: Not applicable.
-
Author contributions: The authors have accepted responsibility for the entire content of this manuscript and approved its submission.
-
Use of Large Language Models, AI and Machine Learning Tools: None declared.
-
Conflict of interest: The authors state no conflict of interest.
-
Research funding: This research was supported by the National Key R&D Program of China, Project No. 2021YFB4001501, the National Natural Science Foundation of China, Project No.62461029, the Fund of Science and Technology Program of Jingdezhen City, Project No. 2023GY001-13, the Fund of Science and Technology Research Project of Jiangxi Provincial Department of Education, Project No.GJJ2400910, the Fund of Science and Technology Program of Guangzhou City, Project No.SL2023A04J01572, and the Fund of Guangdong Basic and Applied Basic Research Foundation, Project No. 2023A1515110166.
-
Data availability: Not applicable.
References
[1] L. James, “Byzantine glass mosaic tesserae: some material considerations,” Byzantine and Modern Greek Stud., vol. 30, pp. 29–47, 2006, https://doi.org/10.1179/030701306X96582.Suche in Google Scholar
[2] E. Neri, C. Morvan, P. Colomban, M. F. Guerra, and V. Prigent, “Late roman and byzantine mosaic opaque “glass-ceramics” tesserae (5th–9th century),” Ceram. Int., vol. 42, pp. 18859–18869, 2016, https://doi.org/10.1016/j.ceramint.2016.09.033.Suche in Google Scholar
[3] B. Lei and C. S. Kim, “Expression forms and application of ceramic materials in mural paintings in architectural environment,” IOP Conf. Ser.: Mater. Sci. Eng., vol. 473, p. 012015, 2019, https://doi.org/10.1088/1757-899X/473/1/012015.Suche in Google Scholar
[4] E. Basso, C. Invernizzi, M. Malagodi, M. F. La Russa, D. Bersani, and P. P. Lottici, “Characterization of colorants and opacifiers in Roman glass mosaic tesserae through spectroscopic and spectrometric techniques,” J. Raman Spectrosc., vol. 45, pp. 238–245, 2014, https://doi.org/10.1002/jrs.4449.Suche in Google Scholar
[5] N. Schibille, P. Degryse, M. Corremans, and C. G. Specht, “Chemical characterisation of glass mosaic tesserae from sixth-century sagalassos (south-west Turkey): chronology and production techniques,” J. Archaeol. Sci., vol. 39, pp. 1480–1492, 2012, https://doi.org/10.1016/j.jas.2012.01.020.Suche in Google Scholar
[6] I. Cayiroglu and B. E. Demir, “Computer assisted glass mosaic tiling automation,” Robot. Comput.-Integr. Manuf., vol. 28, pp. 583–591, 2012, https://doi.org/10.1016/j.rcim.2012.02.008.Suche in Google Scholar
[7] G. Dong, S. Sun, N. Wu, H. Feng, P. Huang, and M. Pan, “Research on automatic mosaic ceramic tiling method based on color matching,” Ceram. Int., vol. 47, pp. 31451–31456, 2021, https://doi.org/10.1016/j.ceramint.2021.08.021.Suche in Google Scholar
[8] G. Dong, R. You, S. Liu, “Mosaic ceramic surface defect detection enhancement algorithm based on guided filter and multi-scale fusion,” Mater. Test., vol. 67, pp. 568–578, 2025, https://doi.org/10.1515/mt-2024-0330.Suche in Google Scholar
[9] S. Kumari, R. Jain, U. Kumar, “Defect identification in friction stir welding using continuous wavelet transform,” J. Intell. Manuf., vol. 30, pp. 483–494, 2019, https://doi.org/10.1007/s10845-016-1259-1.Suche in Google Scholar
[10] J. Schwarzmann and T. Beiküfner, “Online magnetic flux leakage detection of inclusions and inhomogeneities in cold rolled steel plate,” Mater. Test., vol. 64, no. 10, pp. 1512–1526, 2022, https://doi.org/10.1515/mt-2022-0182.Suche in Google Scholar
[11] T. Aydın, E. Erdem, B. Erkayman, M. E. Kocadağistan, and T. Teker, “A novel bearing fault detection approach using a convolutional neural network,” Mater. Test., vol. 66, no. 4, pp. 478–492, 2024, https://doi.org/10.1515/mt-2023-0334.Suche in Google Scholar
[12] H. Wen, Y. Li, Y. Wang, “Usage of an improved YOLOv5 for steel surface defect detection,” Mater. Test., vol. 66, no. 5, pp. 726–735, 2024, https://doi.org/10.1515/mt-2023-0161.Suche in Google Scholar
[13] X. Suo, J. Liu, L. Dong, C. Shengfeng, L. Enhui, and C. Ning, “A machine vision-based defect detection system for nuclear-fuel rod groove,” J. Intell. Manuf., vol. 33, pp. 1649–1663, 2022, https://doi.org/10.1007/s10845-021-01746-7.Suche in Google Scholar
[14] T. Wang, T.-H. Kwok, C. Zhou, and S. Vader, “In-situ droplet inspection and closed-loop control system using machine learning for liquid metal jet printing,” J. Manuf. Syst., vol. 47, pp. 83–92, 2018, https://doi.org/10.1016/j.jmsy.2018.04.003.Suche in Google Scholar
[15] J. Wang, P. Fu, and R. X. Gao, “Machine vision intelligence for product defect inspection based on deep learning and hough transform,” J. Manuf. Syst., vol. 51, pp. 52–60, 2019, https://doi.org/10.1016/j.jmsy.2019.03.002.Suche in Google Scholar
[16] G. Dong, S. Sun, N. Wu, X. Chen, P. Huang, and Z. Wang, “A rapid detection method for the surface defects of mosaic ceramic tiles,” Ceram. Int., vol. 48, pp. 15462–15469, 2022, https://doi.org/10.1016/j.ceramint.2022.02.080.Suche in Google Scholar
[17] X. Xie, J. Xu, and J. Luo, “Analysis of skid damage to cylindrical roller bearing of mainshaft of aeroengine,” J. Mech. Sci. Technol., vol. 34, pp. 3239–3247, 2020, https://doi.org/10.1007/s12206-020-0716-0.Suche in Google Scholar
[18] Y. M. He, Y. Q. He, G. Y. Xiong, and M. F. Zhu, “Application of halcon in digital image and signal,” Appl. Mech. Mater., vol. 716, no. 717, pp. 1338–1340, 2015, https://doi.org/10.4028/www.scientific.net/AMM.716-717.1338.Suche in Google Scholar
[19] G. Dong, S. Sun, Z. Wang, “Application of machine vision-based NDT technology in ceramic surface defect detection – a review,” Mater. Test., vol. 64, pp. 202–219, 2022, https://doi.org/10.1515/mt-2021-2012.Suche in Google Scholar
[20] P. M. Bhatt, R. K. Malhan, P. Rajendran, “Image-based surface defect detection using deep learning: a review,” J. Comput. Inf. Sci. Eng., vol. 21, 2021, https://doi.org/10.1115/1.4049535.Suche in Google Scholar
[21] Y.-K. Zhu, G.-Y. Tian, R.-S. Lu, and H. Zhang, “A review of optical NDT technologies,” Sensors, vol. 11, pp. 7773–7798, 2011, https://doi.org/10.3390/s110807773.Suche in Google Scholar PubMed PubMed Central
[22] L. Li, X. w. Zhang, W. t. Li, X. q. Shao, Y. Xiang, and J. b. Sheng, “Visual inspection method of ceramic bottle surface defects based on niblack optimization,” DTCSE, 2018, https://doi.org/10.12783/dtcse/cmee2017/20002.Suche in Google Scholar
[23] P. Zhou, “Surface crack detection method for ceramic tile based on hessian matrix multi-scale filtering,” Laser Optoelectron. Prog., vol. 57, p. 101022, 2020, https://doi.org/10.3788/LOP57.101022.Suche in Google Scholar
[24] J. Hang, X. Yang, and X. Yu, “Sanitary ceramic surface defect detection method based on neighborhood pixel gray information,” Proc. IECON 2020 – 46th Annu. Conf. IEEE Ind. Electron. Soc., pp. 5337–5342, 2020, https://doi.org/10.1109/IECON43393.2020.9255229.Suche in Google Scholar
[25] W. Chen, B. Zou, C. Huang, “The defect detection of 3D-printed ceramic curved surface parts with low contrast based on deep learning,” Ceram. Int., vol. 49, pp. 2881–2893, 2023, https://doi.org/10.1016/j.ceramint.2022.09.272.Suche in Google Scholar
© 2025 Walter de Gruyter GmbH, Berlin/Boston
