Endüstriyel Kalite Kontrolünde Mermer Anomali Tespit Teknikleri: Kapsamlı Bir Derleme
Abstract views: 27
/ 
PDF downloads: 25
Keywords:
Mermer Kalite Kontrolü, Kusur Tespiti, Derin Öğrenme, Bilgisayarlı Görü, Görüntü Segmentasyonu, Anomali Tespiti, Termal-RGB FüzyonAbstract
Mermer üretim endüstrisinde yüzey kusurlarının tespiti, ürün kalitesi ve ekonomik değer açısından
kritik öneme sahiptir. Geleneksel manuel muayene yöntemleri subjektif, zaman alıcı ve hataya açık
olduğundan, otomatik kusur tespit sistemlerine olan ihtiyaç gün geçtikçe artmaktadır. Bu derleme
çalışması, mermer yüzeylerindeki çatlak, renk değişimi, leke ve doku anomalilerinin tespitinde kullanılan
bilgisayarlı görü ve makine öğrenmesi tekniklerini derleme sistematiği penceresinde ele almaktadır.
Klasik görüntü işleme yöntemlerinden (Gabor filtreleri, LBP, wavelet dönüşümleri) modern derin
öğrenme mimarilerine (U-Net, FPN, YOLO, DeepLabv3+) kadar geniş bir yelpazede teknikler
incelenmiştir. RGB ve termal görüntüleme modalitelerinin füzyonu, özellikle FPN tabanlı modellerde
mIoU değerlerini %87'ye kadar çıkarabilmektedir. Denetimli segmentasyon yöntemleri yüksek
lokalizasyon performansı sunarken, otoenkoder ve metrik öğrenme tabanlı denetimsiz yaklaşımlar etiket
gereksinimini azaltmakta ve dengesiz veri setlerinde daha kararlı sonuçlar vermektedir. YOLOv8-Seg
gibi domain-optimize edilmiş mimariler, endüstriyel uygulamalarda mAP@0.5 değerlerini 0.856
seviyelerine çıkarabilmektedir. Bu çalışmada ayrıca 2020-2025 yılları arasındaki güncel gelişmeler,
performans karşılaştırmaları, uygulama zorlukları ve gelecek araştırma yönelimleri detaylı olarak
tartışılmaktadır. Yapılan kapsamlı araştırmalar neticesinde, multimodal görüntü füzyonu, hafif
segmentasyon mimarileri ve denetimsiz öğrenme yaklaşımlarının entegrasyonu, gerçek zamanlı
endüstriyel uygulamalar için en fazla umut verici teknikler olarak bir adım öne çıkmaktadır.
Downloads
References
Vrochidou, E., Sidiropoulos, G. K., Ouzounis, A. G., Lampoglou, A., Tsimperidis, I., Papakostas, G. A., ... & Sarafis, I. T. (2023). Fusion of Thermal and RGB Images for Automated Deep Learning Based Marble Crack Detection. In 2023 IEEE International Conference on Artificial Intelligence & Internet of Things (AIIoT) (pp. 1-6). IEEE. DOI: 10.1109/AIIoT58121.2023.10174288
Arora, M. (2023). AI-Driven Industry 4.0: Advancing Quality Control through Cutting-Edge Image Processing for Automated Defect Detection. International Journal of Computer Science and Mobile Computing, 12(8), 21-31. DOI: 10.47760/ijcsmc.2023.v12i08.003
Czimmermann, T., Ciuti, G., Milazzo, M., Chiurazzi, M., Roccella, S., Oddo, C. M., & Dario, P. (2020). Visual-Based Defect Detection and Classification Approaches for Industrial Applications—A SURVEY. Sensors, 20(5), 1459. DOI: 10.3390/S20051459
Dionísio, A., Garcia, M. B., & Bento, L. N. (2023). Natural stone heterogeneities and discontinuities: an overview and proposal of a classification system. Bulletin of Engineering Geology and the Environment, 82(4), 1-21. DOI: 10.1007/s10064-023-03152-0
Wu, Y., Yin, C., Pan, L., Wang, X., & Zhang, Y. (2024). A Feature Extraction and Detection Method for Multi-Scale Defects on Mineral Surface. In 2024 7th International Conference on Pattern Recognition and Artificial Intelligence (PRAI) (pp. 1-6). IEEE. DOI: 10.1109/prai62207.2024.10827759
Dogan, H., & Akay, O. (2010). Using AdaBoost classifiers in a hierarchical framework for classifying surface images of marble slabs. Expert Systems with Applications, 37(12), 8814-8821. DOI: 10.1016/J.ESWA.2010.06.019
Forcado, M. R. G., & Estrada, J. E. (2018). Model Development of Marble Quality Identification Using Thresholding, Sobel Edge Detection and Gabor Filter in a Mobile Platform. In 2018 IEEE 10th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment and Management (HNICEM) (pp. 1-6). IEEE. DOI: 10.1109/HNICEM.2018.8666359
Selver, M. A., & Akay, O. (2009). Evaluating clustering methods for classification of marble slabs in an automated industrial marble inspection system. In 2009 International Conference on Electrical and Electronics Engineering-ELECO 2009 (pp. I-169). IEEE. DOI: 10.1109/ELECO.2009.5355261
Karaali, İ., & Eminağaoğlu, M. (2020). A convolutional neural network model for marble quality classification. SN Applied Sciences, 2(10), 1-11. DOI: 10.1007/S42452-020-03520-5
Sipko, E., Kravchenko, O., Karapetyan, A., Ospanov, Y., & Shadrin, A. (2020). The system recognizes surface defects of marble slabs based on segmentation methods. Bulletin of L.N. Gumilyov Eurasian National University. Technical Science and Technology Series, 130(1), 50-58. DOI: 10.37943/AITU.2020.1.63643
Vrochidou, E., Sidiropoulos, G. K., Ouzounis, A. G., Lampoglou, A., Tsimperidis, I., Papakostas, G. A., ... & Sarafis, I. T. (2022). Towards Robotic Marble Resin Application: Crack Detection on Marble Using Deep Learning. Electronics, 11(20), 3289. DOI: 10.3390/electronics11203289
Akosman, S. A., Oktem, M., Moral, O. T., & Yilmaz, A. (2021). Deep Learning-based Semantic Segmentation for Crack Detection on Marbles. In 2021 29th Signal Processing and Communications Applications Conference (SIU) (pp. 1-4). IEEE. DOI: 10.1109/SIU53274.2021.9477867
Shilin, D. V. (2023). Designing the system for detecting unsuitable marble stones for an industrial process using convolutional neural networks. In 2023 4th International Conference on Renewable Energy and Electric Power Engineering (REEPE) (pp. 1-5). IEEE. DOI: 10.1109/REEPE57272.2023.10086731
Tian, Q., Peng, R., & Wang, F. (2025). Segmentation of Stone Slab Cracks Based on an Improved YOLOv8 Algorithm. Applied Sciences, 15(15), 8610. DOI: 10.3390/app15158610
IEEE Access. (2023). A Survey on Unsupervised Anomaly Detection Algorithms for Industrial Images. IEEE Access, 11, 55297-55315. DOI: 10.1109/access.2023.3282993
Vrochidou, E., Sidiropoulos, G., Ouzounis, A. G., Lampoglou, A., Tsimperidis, I., Papakostas, G. A., ... & Sarafis, I. T. (2023). RGB and Thermal Image Analysis for Marble Crack Detection with Deep Learning. In Algorithms for Intelligent Systems (pp. 447-458). Springer. DOI: 10.1007/978-981-99-4626-6_36
Pan, S. J., & Yang, Q. (2010). A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345-1359.
Abdullah, Y., & Öz, C. (2024). Marble Surface Anomaly Detection Using Autoencoder Architecture. Journal of Electrical Engineering, Electronics, Control and Computer Science, 18(1), 1-8. DOI: 10.21776/jeeccis.v18i1.1685
Schroff, F., Kalenichenko, D., & Philbin, J. (2015). FaceNet: A unified embedding for face recognition and clustering. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 815-823).
Hoffer, E., & Ailon, N. (2015). Deep metric learning using triplet network. In International Workshop on Similarity-Based Pattern Recognition (pp. 84-92). Springer.
Ruff, L., Vandermeulen, R., Goernitz, N., Deecke, L., Siddiqui, S. A., Binder, A., ... & Kloft, M. (2018). Deep one-class classification. In International Conference on Machine Learning (pp. 4393-4402). PMLR.
Sidiropoulos, G. K., Ouzounis, A. G., Papakostas, G. A., Sarafis, I. T., Stamkos, A., & Solakis, I. (2022). Hand-Crafted and Learned Feature Aggregation for Visual Marble Tiles Screening. Journal of Imaging, 8(7), 191. DOI: 10.3390/jimaging8070191
Dietterich, T. G. (2000). Ensemble methods in machine learning. In International Workshop on Multiple Classifier Systems (pp. 1-15). Springer.
Malamas, E. N., Petrakis, E. G., Zervakis, M., Petit, L., & Legat, J. D. (2003). A survey on industrial vision systems, applications and tools. Image and Vision Computing, 21(2), 171-188.
Whitehouse, D. J. (2011). Handbook of Surface and Nanometrology (2nd ed.). CRC Press.
Tantussi, G., & Lanzetta, M. (2007). Analyses of stone surfaces by optical methods. In Proceedings of the 10th International Conference on Stone (pp. 1-8).
Sipko, E., Kravchenko, O., Karapetyan, A., Ospanov, Y., & Shadrin, A. (2020). The system recognizes surface defects of marble slabs based on segmentation methods. Bulletin of L.N. Gumilyov Eurasian National University, 130(1), 50-58.
Wu, Y., Yin, C., Pan, L., Wang, X., & Zhang, Y. (2024). A Feature Extraction and Detection Method for Multi-Scale Defects on Mineral Surface. In 2024 PRAI Conference Proceedings.
Vrochidou, E., Sidiropoulos, G. K., Ouzounis, A. G., Lampoglou, A., Tsimperidis, I., Papakostas, G. A., ... & Sarafis, I. T. (2022). Towards Robotic Marble Resin Application: Crack Detection on Marble Using Deep Learning. Electronics, 11(20), 3289.
Bergmann, P., Fauser, M., Sattlegger, D., & Steger, C. (2019). MVTec AD—A comprehensive real-world dataset for unsupervised anomaly detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 9592-9600).
Buda, M., Maki, A., & Mazurowski, M. A. (2018). A systematic study of the class imbalance problem in convolutional neural networks. Neural Networks, 106, 249-259.
Wang, M., & Deng, W. (2018). Deep visual domain adaptation: A survey. Neurocomputing, 312, 135-153.
Dwivedi, S. K., Vishwakarma, M., & Soni, A. (2018). Advances and researches on non destructive testing: A review. Materials Today: Proceedings, 5(2), 3690-3698.
