Identification and Classification of Cracks in Traditional Pottery from West Sumatra Using Digital Image Processing
DOI:
https://doi.org/10.30871/jaic.v10i1.12156Keywords:
Cultural Heritage, Digital Image Processing, Image Segmentation, Morphological Operation, Pottery Crack DetectionAbstract
Cracks in traditional West Sumatran pottery are a major challenge in preserving this cultural heritage. With age and the manual manufacturing process, pottery becomes highly susceptible to physical damage, particularly cracks on the surface and internal structure. These cracks not only affect the functional and aesthetic value but also reduce the cultural and economic value of the pottery. Therefore, an accurate early identification system is crucial to ensure the survival and preservation of this culture. This study developed a digital image processing-based system to detect and classify cracks in traditional pottery. The system integrates image preprocessing, including cropping, resizing, grayscale conversion, contrast stretching, and histogram equalization to improve image quality and highlight thin and irregular cracks. Image segmentation was performed using the Multi-Threshold Otsu method to separate cracks from the background, while classification was performed using a convolutional neural network (CNN). Experimental results show that this system is able to achieve an accuracy of 94.8%, precision of 93.5%, recall of 92.3%, and F1-score of 92.9%, indicating the system's ability to accurately detect cracks. Comparisons with other segmentation and classification methods are needed to provide a more comprehensive picture of the effectiveness of this approach. The implementation of this system is expected to support the preservation of traditional Minangkabau pottery through digitalization, provide an ornament database that can be accessed by researchers, artists, and the general public, and assist in more efficient cultural documentation and archiving.
Downloads
References
[1] X. Wang and B. Chen, “Artificial intelligence for cultural heritage : digital processing-based techniques and research challenges Artificial intelligence for cultural heritage : digital image processing-based techniques and research challenges Xiaonan Wang and Baozhong Chen *,” no. May, 2025, doi: 10.1504/IJICT.2025.10070954.
[2] Y. Wu, S. Li, J. Li, Y. Yu, J. Li, and Y. Li, “Journal of Infrastructure Intelligence and Resilience Deep learning in crack detection : A comprehensive scientometric review,” vol. 4, no. February, 2025.
[3] M. A. Ilani, L. Amini, H. Karimi, and M. S. Kuhshuri, “CNN-based Labelled Crack Detection for Image Annotation”.
[4] M. Sabha, M. Saffarini, and R. Yousef, “Image classification in cultural heritage,” vol. 13, no. 4, pp. 4722–4735, 2024, doi: 10.11591/ijai.v13.i4.pp4722-4735.
[5] D. Shojaei, P. Jafary, and Z. Zhang, “Mixed Reality-Based Concrete Crack Detection and Skeleton Extraction Using Deep Learning and Image Processing,” 2024.
[6] S. Gokak, P. Khichade, N. Heggalagi, A. Billowria, and S. Hegde, “Defect Detection and Classification of Cultural Heritage Buildings Using Deep Learning Section II - Background :,” vol. 3, no. Incoft, pp. 619–626, 2025, doi: 10.5220/0013633700004664.
[7] S. Niu, “Image Processing Based on Convolution Neural Network,” pp. 1–8, 2025.
[8] J. Zhou, H. Li, L. Lu, and Y. Cheng, “Machine Vision-Based Surface Defect Detection Study for Ceramic 3D Printing,” pp. 1–15, 2024.
[9] M. Bahrami and A. Albadvi, “H ERITAGE B UILDINGS IN N EED OF C ONSERVATION U SING I MAGE C LASSIFICATION AND G RAD -CAM ∗,” 2023.
[10] J. Diao, H. Wei, Y. Zhou, and Z. Diao, “A Deep Learning-Based Algorithm for Ceramic Product Defect Detection,” pp. 1–19, 2025.
[11] N. Karimi, M. Mishra, and P. B. Lourenço, “Deep learning-based automated tile defect detection system for Portuguese cultural heritage buildings,” J. Cult. Herit., vol. 68, pp. 86–98, 2024, doi: 10.1016/j.culher.2024.05.009.
[12] S. S. Zadeh, S. Aalipour, M. Khorshidi, and F. Kooban, “Concrete Surface Crack Detection with Convolutional-based Deep Learning Models,” vol. 10, no. 3, pp. 25–35, 2023.
[13] H. M. Structures, “Deep Learning-Based Automated Detection of Cracks in Historical Masonry Structures,” 2023.
[14] M. Ikhsan and M. Rahardi, “Image-Based Classification of Indonesian Traditional Houses Using a Hybrid CNN-SVM Algorithm,” vol. 9, no. 5, pp. 2303–2309, 2025.
[15] E. Ogun and Y. A. Voeurn, “A Real-Time Mobile Robotic System for Crack Detection in Construction Using Two-Stage Deep Learning,” pp. 1–28, 2026.
[16] S. Roy, B. Yogi, R. Majumdar, P. Ghosh, and S. Kumar, “Deep learning ‑ based crack detection and prediction for structural health monitoring,” 2025.
[17] Y. Zhang, X. Liu, W. Sun, T. You, and X. Qi, “Multi-Threshold Remote Sensing Image Segmentation Based on Improved Black-Winged Kite Algorithm,” pp. 1–24, 2025.
[18] A. Raza, F. Hanif, and H. A. Mohammed, “Efficient crack and surface- type recognition via CNN-block development mechanism and edge profiling,” pp. 1–25, 2025.
[19] A. Nur, A. Thohari, A. Karima, K. Santoso, and R. Rahmawati, “Crack Detection in Building Through Deep Learning Feature Extraction and Machine Learning Approach,” vol. 8, no. 1, pp. 1–6, 2024.
[20] A. Ranieri, G. Palmieri, and S. Biasotti, “Artifacts Using Semantic Segmentation”.
[21] N. M. Pawar, “Deep Learning Framework for Infrastructure Maintenance: Crack Detection and High-Resolution Imaging of Infrastructure Surfaces,” pp. 1–14.
[22] S. Deshpande, V. Venugopal, M. Kumar, and S. Anand, “Deep learning ‑ based image segmentation for defect detection in additive manufacturing : an overview,” Int. J. Adv. Manuf. Technol., pp. 2081–2105, 2024, doi: 10.1007/s00170-024-14191-6.
[23] Y. Wang, L. Zhang, X. Zhao, B. Tang, and W. Yang, “Review of Research on Ceramic Surface Defect Detection Based on Deep Learning,” pp. 1–19, 2025.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Raja Ayu Mahessya, Firna Yenila
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
