Classification of Marble Types Using Machine Learning Techniques

Year 2023, Volume: 6 Issue: 1, 33 - 42, 15.06.2023

Murat Yavuz , İbrahim Türkoğlu

https://doi.org/10.53448/akuumubd.1268931

Abstract

Natural stones are one of the indispensable elements of people from shelter to weapons. Among these stone types, marbles and marble-derived products are among the objects that people always prefer, from bathroom to kitchen, from garden design to small decorative home decorations. While the marbles are named according to the regions where they are extracted, their types and qualities are classified based on observation by people who are qualified as experts in this field. This classification, which is made by experts based on observation, carries risks in economic terms, increases the workload and is a difficult process with a high error rate. These processes need a fast, easy and highly accurate digital transformation. In this study, feature extraction was done by using deep learning in the species classification of marbles. The extracted features were classified using machine learning techniques. As a result of the application made with the data set consisting of 3703 marble and marble-derived natural stone images belonging to 28 different species, a classification success of 99.7% was obtained with the DenseNet deep learning model and the K-Nearest Neighbor method.

Keywords

Marble, Deep Learning, Machine Learning, Image Processing

Supporting Institution

Fırat Üniversitesi

Project Number

TEKF.22.29.

Thanks

This study was supported by the Fırat University Scientific Research Unit with the project numbered TEKF.22.29

Mermer Türlerinin Makine Öğrenmesi Teknikleri Kullanılarak Sınıflandırılması

Abstract

Doğal taşlar, insanların barınmadan silaha kadar vazgeçilmez unsurlarından bir tanesidir. Bu taş türleri içerisinde mermerler ve mermer türevli ürünler banyodan mutfağa, bahçe tasarımından küçük dekoratif ev süslerine kadar insanların sürekli tercih ettiği objelerdendir. Mermerler çıkarıldıkları bölgelere göre isimlendirilirken bu alanda uzman olarak nitelendirilen kişiler tarafından gözleme dayalı olarak türleri ve kaliteleri sınıflandırılmaktadır. Uzman kişilerin gözleme dayalı yaptığı bu sınıflandırma ekonomik anlamda risk taşımakta, iş yükünü arttırmakta ve hata oranı yüksek olabilen zorlu bir süreçtir. Bu süreçlerin hızlı, kolay ve doğruluk oranı yüksek bir dijital dönüşüme ihtiyacı bulunmaktadır. Bu çalışmada mermerlerin tür sınıflandırmasında derin öğrenme kullanılarak özellik çıkarımı yapılmıştır. Çıkarılan özellikler makine öğrenme teknikleri kullanılarak sınıflandırma uygulaması gerçekleştirilmiştir. 28 ayrı türe ait 3703 mermer ve mermer türevli doğal taş imgesinden oluşan veri seti ile yapılan uygulamanın test sonucunda DenseNet derin öğrenme modeli ve K-En Yakın Komşu metodu ile %99,7’lik sınıflandırma başarımı elde edilmiştir.

Keywords

Mermer, Derin Öğrenme, Makine Öğrenmesi, Görüntü İşleme

Project Number

TEKF.22.29.

References

• Canayaz M. and Uludağ F., 2020. Marble classıfıcatıon usıng deep neural networks, European Journal of Technic, 10 (1), 52 – 63.
• Chollet, F. 2017. Xception: deep learning with depthwise separable convolutions. Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, 1800 – 1807.
• Doğan F. and Türkoğlu İ., 2019. Derin öğrenme modelleri ve uygulama alanlarına ilişkin bir derleme. Dicle Üniversitesi Mühendislik Fakültesi Mühendislik Dergisi, 10 (2), 409 – 445.
• Doyle-Kent, M. and Kopacek P., 2020, Is the manufacturing ındustry on the cusp of a new revolution? Proceedings of the International Symposium for Production Research, 432 – 441.
• Duda, R.O., Hart, P.E. and Stork D.G., 2001. Pattern Classification, Wiley Interscience, 462 – 463.
• Elmas, B., 2022. Classification varieties of marble and granite by convolutional neural networks with transfer learning method. Journal of the Faculty of Engineering and Architecture of Gazi University, 37 (2), 985 –1001.
• Freund, Y. and Schapire, R. E., 1999. A short ıntroduction to boosting. In Journal of Japanese Society for Artificial Intelligence, 14 (5), 771 – 780.
• Goldberg D.E. and Holland J.H., 1988. Genetic algorithms and machine learning. Kluwer Academic Publishers, Machine Learning 3, 95 – 99.
• Gültepe, Y., 2019. Makine öğrenmesi algoritmaları ile hava kirliliği tahmini üzerine karşılaştırmalı bir değerlendirme. European Journal of Science and Technology, 16, 8 – 15.
• Hinton G.E. and Salakhutdinov R.R. 2006. Reducing the dimensionality of data with neural networks. Science, 313 (5786), 504 – 507.
• Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M. and Adam, H., 2017. Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861
• Huang, G., Liu, Z., Van der Maaten, L. and Weinberger, K. Q., 2017. Densely connected convolutional networks. Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, 2261 – 2269.
• Karaali, İ. and Eminağaoğlu, M., 2020. A convolutional neural network model for marble quality classification. Journal of the Faculty of Engineering and Architecture of Gazi University, 36 (1) , 347 – 357.
• Karakoyun, M. and Hacıbeyoğlu, M., 2014. Statistical comparison of machine learning classification algorithms using biomedical data sets, Dokuz Eylül Üniversitesi, Mühendislik Fakültesi Mühendislik Bilimleri Dergisi, 16 (48), 30 – 41.
• Kızrak, M. A. and Bolat, B., 2018. Derin öğrenme ile kalabalık analizi üzerine detaylı bir araştırma. Bilişim Teknolojileri Dergisi, 11 (3), 263 – 286.
• Kononenko, I., 2001, Machine learning for medical diagnosis: history, state of the art and perspective. Artifical Intelligence in Medicine, 23, 89 – 109.
• Martínez-Alajarín, J., Luis-Delgado, J. D. and Tomás-Balibrea, L. M., 2005. Automatic system for quality-based classification of marble textures. IEEE Transactions on Systems, Man and Cybernetics Part C: Applications and Reviews, 35 (4), 488 – 497.
• Masters, D. and Luschi, C., 2018. Revisiting small batch training for deep neural networks. arXiv preprint arXiv:1804.07612
• Özkan Y., 2013. Veri Madenciliği Yöntemleri. Dr. Rifat Çölkesen, Papatya Yayınları.
• Pençe, İ. and Şişeci Çeşmeli, M., 2019. Deep learning in marble slabs classification, Techno-Science - Scientific Journal of Mehmet Akif Ersoy University, 2 (1) , 21 – 26.
• Sayılgan, E., Yüce, Y. K. and İşler, Y., 2021. Evaluation of wavelet features selected via statistical evidence from steady-state visuallyevoked potentials to predict the stimulating frequency. Journal of the Faculty of Engineering and Architecture of Gazi University, 36 (2), 593 – 605.
• Selver, M. A., Akay, O., Ardalı, E., Yavuz, B. A., Önal, O. and Özden, G., 2009. Cascaded and hierarchical neural networks for classifying surface images of marble slabs. IEEE Transactions on Systems, Man and Cybernetics Part C: Applications and Reviews, 39 (4) , 426 – 439.
• Simonyan, K. and Zisserman, A., 2015. Very deep convolutional networks for large-scale ımage recognition. arXiv preprint arXiv:1409.1556
• Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J. and Wojna, Z., 2016. Rethinking the ınception architecture for computer vision. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2818 – 2826.
• Topalova, I.C. and Tzokev, A., 2011. Adaptıve marble plate classıfıcatıon system based on neural network and plc ımplementatıon, Annals of DAAAM for 2011 & Proceedings of the 22nd International DAAAM Symposium, 22, 453 – 454.
• Torun, Y., Akbaş, M.R., Çelik, M.A. and Kaynar, O., 2019. Development a machine vision system for marble classification, 27th Signal Processing and Communications Applications Conference (SIU).