Inception V3-Based Deep Learning Approach forCrack Detection in Paintings

  • Authors

    • Dr. Rajendra Vasantrao Patil Department of Computer Engineering, SSVPS Bapusaheb Shivajirao Deore College of Engineering, Dhule (MS), India
    • Dr. Govind Mohanlal Poddar NES Gangamai College of Engineering, Nagaon, Dhule (MS)‎،‎ India
    • Deepak Yashwantrao Bhadane R. C. Patel College of Engineering and Polytechnic, Shirpur, Dhule (M. S.)‎،‎ India
    • Dr. Rahul Manohar Patil NES Gangamai College of Engineering, Nagaon, Dhule (MS)‎،‎ India
    • Shravani R. Patil Department of Computer Engineering, SSVPS Bapusaheb Shivajirao Deore College of Engineering, Dhule (MS), India
    • Dr. Sunil Vikram Desale Nikam Institute of Technology and Research, Dhule, India
    • Vishal D. Suryawanshi Department of Computer Engineering, SSVPS Bapusaheb Shivajirao Deore College of Engineering, Dhule (MS), India
    https://doi.org/10.14419/4jfvmz41

    Received date: July 17, 2025

    Accepted date: August 19, 2025

    Published date: August 27, 2025

  • Crack Detection; Painting Preservation; Deep Learning; CNN; Inceptionv3; Surface Defects

  • Abstract

    This study proposes a deep learning-based methodology for the automatic detection of surface cracks in painting artworks, an essential task ‎in art restoration and preservation. A dataset comprising 700 high-resolution images (350 cracked, 350 non-cracked) was curated and expanded through data augmentation techniques to enhance model generalization. Preprocessing steps included resizing and normalization. Four deep ‎learning models, VGG16, ResNet50, a custom CNN, and InceptionV3, were evaluated. Among them, a fine-tuned InceptionV3 model ‎yielded the best performance, achieving a test accuracy of 98.01% and an F1 score of 0.98. Evaluation metrics such as confusion matrix, ‎accuracy/loss curves, and classification report validated the robustness of the proposed method. Compared to earlier approaches that were ‎restricted to structural domains or limited art-specific studies, the proposed framework demonstrates superior accuracy and broader applicability through transfer learning and advanced regularization. The system offers a scalable, non-invasive solution for digital inspection of ‎artworks and can be extended to diverse painting types, varied mediums, or severity-based crack classification. It also aligns with emerging ‎trends in lightweight, attention-guided deep learning models, supporting real-world deployment in cultural heritage preservation‎.

  • References

    1. Y.-J. Cha, W. Choi, and O. Büyüköztürk, “Deep learning-based crack damage detection using convolutional neural networks,” Comput.-Aided Civ. Infrastruct. Eng., vol. 32, no. 5, pp. 361–378, May 2017, https://doi.org/10.1111/mice.12263.
    2. L. Zhang, F. Yang, Y. D. Zhang, and Y. J. Zhu, “Road crack detection using deep convolutional neural network,” in Proc. IEEE Int. Conf. Image Process. (ICIP), 2016, pp. 3708–3712. https://doi.org/10.1109/ICIP.2016.7533052.
    3. Y. Wu, S. Li, J. Li, Y. Yu, J. Li, and Y. Li, “Deep learning in crack detection: A comprehensive scientometric review,” J. Infrastruct. Intell. Resil., vol. 4, no. 3, p. 100144, 2025, https://doi.org/10.1016/j.iintel.2025.100144.
    4. V. Badrinarayanan, A. Kendall and R. Cipolla, "SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, no. 12, pp. 2481-2495, 1 Dec. 2017, https://doi.org/10.1109/TPAMI.2016.2644615.
    5. K. He, X. Zhang, S. Ren and J. Sun, "Deep Residual Learning for Image Recognition," 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 2016, pp. 770-778, https://doi.org/10.1109/CVPR.2016.90.
    6. K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” in Proc. Int. Conf. Learn. Represent. (ICLR), 2015.
    7. C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens and Z. Wojna, "Rethinking the Inception Architecture for Computer Vision," 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 2016, pp. 2818-2826, https://doi.org/10.1109/CVPR.2016.308.
    8. O. Ronneberger, P. Fischer, and T. Brox, “U-Net: Convolutional networks for biomedical image segmentation,” in Proc. Int. Conf. Med. Image Comput. Comput.-Assist. Intervent. (MICCAI), 2015, pp. 234–241. https://doi.org/10.1007/978-3-319-24574-4_28.
    9. G. Huang, Z. Liu, L. Van Der Maaten and K. Q. Weinberger, "Densely Connected Convolutional Networks," 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, 2017, pp. 2261-2269, https://doi.org/10.1109/CVPR.2017.243.
    10. T. -Y. Lin, P. Goyal, R. Girshick, K. He and P. Dollár, "Focal Loss for Dense Object Detection," 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy, 2017, pp. 2999-3007, https://doi.org/10.1109/ICCV.2017.324.
    11. H. Maeda, Y. Sekimoto, T. Seto, T. Kashiyama, and H. Omata, “Road damage detection and classification using deep neural networks with smartphone images,” Comput.-Aided Civ. Infrastruct. Eng., vol. 33, no. 12, pp. 1127–1141, 2018. https://doi.org/10.1111/mice.12387.
    12. Yu Zhang, Xin Gao, and Hanzhong Zhang, "Deep Learning-Based Semantic Segmentation Methods for Pavement Cracks" Information 14, no. 3: 182, 2023. https://doi.org/10.3390/info14030182.
    13. K. Gopalakrishnan, S. K. Khaitan, A. Choudhary, and A. Agrawal, “Deep convolutional neural networks with transfer learning for computer vi-sion-based data-driven pavement distress detection,” Constr. Build. Mater., vol. 157, pp. 322–330, 2017. https://doi.org/10.1016/j.conbuildmat.2017.09.110.
    14. Guoshao Su, Yuanzhuo Qin, Huajie Xu, Jinfu Liang, "Automatic real-time crack detection using lightweight deep learning models”, Engineering Applications of Artificial Intelligence,Volume 138, Part A, 2024, 109340, https://doi.org/10.1016/j.engappai.2024.109340.
    15. Yuan, Qi, Yufeng Shi, and Mingyue Li, "A Review of Computer Vision-Based Crack Detection Methods in Civil Infrastructure: Progress and Challenges" Remote Sensing 16, no. 16: 2910, 2024 https://doi.org/10.3390/rs16162910.
    16. Hyunjun Kim, Sung-Han Sim, Billie F. Spencer, “Automated concrete crack evaluation using stereo vision with two different focal lengths”, Au-tomation in Construction, vol. 135, 104136, 2022, https://doi.org/10.1016/j.autcon.2022.104136.
    17. Y. Ni, T. Shi, F. Wu, and Y. Liu, “Surface defect detection for painted images using attention-guided CNN,” Appl. Sci., vol. 10, no. 17, p. 6062, 2020.
    18. F. Wei, Y. Jiao, Z. Huangfu, G. Shi, N. Wang, H. Dong. “Weakly-supervised segmentation with ensemble explainable AI: A comprehensive evalua-tion on crack detection”, Rev Sci Instrum., 96(4), 045106, 2025https://doi.org/10.1063/5.0249805.
    19. Y. Chen, J. Pan, J. Lei, D. Zeng, Z. Wu and C. Chen, "EEE-Net: Efficient Edge Enhanced Network for Surface Defect Detection of Glass," in IEEE Transactions on Instrumentation and Measurement, vol. 72, pp. 1-13, 2023. https://doi.org/10.1109/TIM.2023.3320746.
    20. Tingyang Chen, Zhenhua Cai, Xi Zhao, Chen Chen, Xufeng Liang, Tierui Zou, Pan Wang, “Pavement crack detection and recognition using the architecture of segNet”, Journal of Industrial Information Integration, Vol. 18, 100144, 2020, https://doi.org/10.1016/j.jii.2020.100144.
    21. A. Hussain, A. Aslam,, “Ensemble-based approach using inception V2, VGG-16, and Xception convolutional neural networks for surface cracks detection”, Journal of Applied Research and Technology, 22(4), 586–598, 2024 https://doi.org/10.22201/icat.24486736e.2024.22.4.2431.
    22. S. Ren, K. He, R. Girshick and J. Sun, "Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks," in IEEE Transac-tions on Pattern Analysis and Machine Intelligence, vol. 39, no. 6, pp. 1137-1149, 1 June 2017, https://doi.org/10.1109/TPAMI.2016.2577031.
    23. Hongxia Li, Weixing Wang, Mengfei Wang, Limin Li, Vivian Vimlund, “A review of deep learning methods for pixel-level crack detection”, Jour-nal of Traffic and Transportation Engineering, Vol. 9 (6), pp. 945-968, 2022. https://doi.org/10.1016/j.jtte.2022.11.003.
    24. C. Kanellakis and G. Nikolakopoulos, “Survey on computer vision for UAVs: Current developments and trends,” J. Intell. Robot. Syst., vol. 87, no. 1, pp. 141–168, 2017. https://doi.org/10.1007/s10846-017-0483-z.
    25. T. Song, T. Chen, Y. Gong, Y. Wang, L. Ran, J. Chen, H. Tang, and Z. Zou, “Enhanced Sagger Crack Detection Integrating Deep Learning and Machine Vision,” Electronics, vol. 13, no. 24, p. 5010, 2024, https://doi.org/10.3390/electronics13245010.
    26. X. Liu, J. Zhu, L. Zhang, and Z. Li, “Robust crack detection in masonry structures with transformers,” Measurement, vol. 195, p. 111590, 2022, https://doi.org/10.1016/j.measurement.2022.111590.
    27. A. Islam, Y. Zhang, and M. J. Islam, “Vision transformer-based autonomous crack detection on asphalt and concrete surfaces,” Autom. Constr., vol. 139, p. 104316, 2022, https://doi.org/10.1016/j.autcon.2022.104316.
    28. Min Feng, and Xu Juncai, "Lightweight Dual-Attention Network for Concrete Crack Segmentation" Sensors 25, no. 14: 4436, 2025 https://doi.org/10.3390/s25144436.
    29. R. Gupta and P. Verma, “Resilient lightweight CNN with coordinate attention for industrial surface defect detection,” IEEE Trans. Instrum. Meas., vol. 72, pp. 1–12, 2023, https://doi.org/10.1109/TIM.2023.3246499.
    30. A. A. Alkannad et al., "CrackVision: Effective Concrete Crack Detection with Deep Learning and Transfer Learning," in IEEE Access, vol. 13, pp. 29554-29576, 2025, https://doi.org/10.1109/ACCESS.2025.3540841.
    31. C. Gode, B. M. Nanche, D. Dhabliya, R. D. Shelke, , R. V. Patil. & Shushma Bhosle, “Dynamic neural architecture search: A pathway to efficient-ly optimized deep learning models” , Journal of Information and Optimization Sciences, 46:4-A, 1117–1127, 20-25. https://doi.org/10.47974/JIOS-1896.
    32. R. V. Patil, V, R. Gosavi, G. M. Poddar, S. K. Swarnkar, “Comparative Study of Traditional Edge Detection Methods and Phase Congruency Based Method”, International Journal of Informatics and Communication Technology (IJ-ICT), vol.14, no. 3, pp. 868-880, 2025. https://doi.org/10.11591/ijict.v14i3.pp868-880.
    33. J. S. R, R. V. Patil, Y. S, P. M, S. S and R. Maranan, "Spilled Deep Capsule Neural Network with Skill Optimization Algorithm for Breast Cancer Recognition in Mammograms," 2025 International Conference on Inventive Computation Technologies (ICICT), Kirtipur, Nepal, 2025, pp. 632-637, https://doi.org/10.1109/ICICT64420.2025.11004784.
    34. R. V. Patil, R. M. Patil, D. Y. Bhadane, G. M. Poddar, A. L. Wakekar, & S. R. Patil, “Adaptive Cheetah Optimization-Driven CNN: A Hybrid Approach for Robust Image Segmentation.”, International Journal of Basic and Applied Sciences, 14(2), 691-702, Aug. 2025. https://doi.org/10.14419/c62avh78.
    35. Rajendra V. Patil, Renu Aggarwal, ”Comprehensive Review on Image Segmentation Applications”, Sci.Int.(Lahore), 35(5), pp. 573-579, Sep. 2023.

  • Downloads

  • How to Cite

    Patil, D. R. V. ., Poddar, D. G. M. ., Bhadane, D. Y. ., Patil , D. R. M. ., Patil, S. R. ., Desale, D. S. V. ., & Suryawanshi, V. D. . (2025). Inception V3-Based Deep Learning Approach forCrack Detection in Paintings. International Journal of Basic and Applied Sciences, 14(4), 756-762. https://doi.org/10.14419/4jfvmz41