Performance Evaluation of Deep Learning Architectures for Tile Defect Detection
DOI:
https://doi.org/10.64470/elene.2025.16Keywords:
Deep Learning, Image Processing, Tile Defect Detection, Transfer LearningAbstract
In this study, an artificial intelligence-based quality control system was developed for the automatic detection and classification of defects in a tile. The dataset created to reduce human-induced errors in the production process and increase inspection accuracy consists of a total of 405 images.
During the model development phase, CNN, MobileNetV2, ResNet50, and EfficientNetB0 architectures were used. The performance of the models was evaluated using the 10-fold cross-validation method for an objective comparison.
The experimental results show that the EfficientNetB0 architecture achieved the highest performance with an accuracy rate of 96.73%. ResNet50 achieved 95.45%, CNN achieved 94.91%, and MobileNetV2 achieved 92.36% accuracy.
Downloads
References
Abdullayeva, E. & Kahramanli Örnek, H. (2024). Diagnosing Epilepsy from EEG Using Machine Learning and Welch Spectral Analysis, Traitement du Signal Vol. 41, No. 2, April, 2024, pp. 971-977, https://doi.org/10.18280/ts.410237
Elbehiery, H., Hefnawy, A. and Elewa, M. (2007). Surface Defects Detection for Ceramic Tiles Using Image Processing and Morphological Techniques, World Academy of Science, Engineering and Technology, 5
Golkar, E., Patel, A., Yazdi, L. & Prabuwono, A.S. (2011). Ceramic Tile Border Defect Detection Algorithms in Automated Visual Inspection System, Journal of American Science, 7(6).
He, K., Zhang, X., Ren, S. & Sun, J. (2016). 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.
Hocenski, Z & Keser, T. (2007). Failure detection and isolation in ceramic tile edges based on contour descriptor analysis, Mediterranean Conference on Control & Automation, Athens, Greece, pp. 1-6, https://doi.org/10.1109/MED.2007.4433713.
Khan, A., Sohail, A., Zahoora, U., & Qureshi, A. S. (2019). A survey of the recent architectures of deep convolutional neural networks. arXiv preprint arXiv:1901.06032.
LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436–444. https://doi.org/10.1038/nature14539
Li, Y., Yang, T., Peng, S., & Liu, Y. (2020). A survey of convolutional neural networks: Analysis, applications, and prospects. arXiv preprint arXiv:2004.02806.
Lu, Q., Lin, J., Luo, L., Zhang, Y. & Zhu, W. (2022). A supervised approach for automated surface defect detection in ceramic tile quality control, Advanced Engineering Informatics, 53, 101692. https://doi.org/10.1016/j.aei.2022.101692
Michalak, J. (2021). Ceramic Tile Adhesives from the Producer’s Perspective: A Literature Review. Ceramics, 4, 378–390. https://doi.org/10.3390/ceramics4030027
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L.C. (2018). MobileNetV2: Inverted residuals and linear bottlenecks. arXiv preprint arXiv:1801.04381
Tan, M. & Le, Q.V. (2019) EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. Proceedings of the 36th International Conference on Machine Learning, 6105-6114.
Younesi, E., Ansari, R., Fazli, M., Ejlali, A., Shafique, M., & Henkel, J. (2024). A comprehensive survey of convolutions in deep learning. arXiv preprint arXiv:2402.15490.
Downloads
Published
Data Availability Statement
The dataset used in this study originates from Ayça Demir’s senior capstone project. After the article is published, the data will be made available for researchers.
Issue
Section
License
Copyright (c) 2025 Ayça Demir, Humar Kahramanlı Örnek
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors retain copyright of their work and grant the journal the right to publish it under the Creative Commons Attribution 4.0 International License (CC BY 4.0). This allows for maximum dissemination and reuse with appropriate citation.
ORCID 
