Derin Öğrenme Tabanlı Mermer Yüzeylerinin Otomatik Sınıflandırılması
Yıl 2021,
Sayı: 26 - Ejosat Özel Sayı 2021 (HORA), 73 - 77, 31.07.2021
Mert Öktem
,
Şahin Alp Akosman
,
Özge Taylan Moral
,
Volkan Kılıç
Öz
Doğal taşların mimaride ve dekorasyonda kullanımının artmasıyla mermere olan talep son yıllarda giderek yükselmiştir. Yükselen talebi karşılayabilmek için üreticilerin kapasite artırımı kadar, mermer üretim süreçlerinin verimliliğini de artırmaları gerekmektedir. Mermer üretim süreçlerinden biri olan mermer sınıflandırılmasında yapılan insan kaynaklı hatalardan dolayı üretim hızı ve verimi düşmektedir. Bu çalışmada, mermerlerin yanlış sınıflandırma problemine çözüm olarak farklı renk ve dokulara sahip mermer türlerinin yüksek başarımla sınıflandıran yapay zeka destekli bir sistem önerilmektedir. Önerilen sistemde, 5 farklı mermer türüne ait 516 mermer görüntüsünün sınıflandırılması için 12 evrişimsel sinir ağı mimarisi, transfer öğrenme ve derin öğrenme yöntemleri kullanılarak eğitilmiştir. Artırılmış veri kümesi ile yapılan eğitimler sonucunda transfer öğrenme uygulanan VGG-16 mimarisi ile %96.07 sınıflandırma başarısı elde edilmiştir. Önerilen sistem, benzer çalışmalardan farklı olarak, geliştirdiğimiz arayüz ile birleştirilmiştir. Böylelikle, üretim sürecinde daha az insan kaynaklı hata ile mermerlerin sınıflandırılmasına katkı sağlanması amaçlanmıştır.
Kaynakça
- Benavente, N., & Pina, P. (2009). Morphological segmentation and classification of marble textures at macroscopical scale. J Computers geosciences, 35(6), 1194-1204.
- Buduma, N., & Locascio, N. (2017). Fundamentals of deep learning: Designing next-generation machine intelligence algorithms: " O'Reilly Media, Inc.".
- Cheung, K. S. (2006). Modelling and analysis of manufacturing systems using augmented marked graphs. J Information Technology Control, 35(1).
- Ferreira, A., & Giraldi, G. (2017). Convolutional Neural Network approaches to granite tiles classification. J Expert Systems with Applications, 84, 1-11.
- Fırıldak, K., & Talu, M. F. (2019). Evrişimsel Sinir Ağlarında Kullanılan Transfer Öğrenme Yaklaşımlarının İncelenmesi. J Bilgisayar Bilimleri, 4(2), 88-95.
- KardanMoghaddama, H., Rajaeib, A., & Moghaddam, H. K. (2018). Marble slabs classification system based on image processing (ark marble mine in Birjand). J Civil Engineering Journal, 4(1).
- Kurt, F. (2018). Evrişimli Sinir Ağlarında Hiper Parametrelerin Etkisinin İncelenmesi. Hacettepe Üniversitesi Fen Bilimleri Enstitüsü,
- López, M., Martínez, J., Matías, J. M., Taboada, J., & Vilán, J. A. (2010). Functional classification of ornamental stone using machine learning techniques. Journal of Computational Applied Mathematics, 234(4), 1338-1345.
- Martínez-Alajarín, J., Luis-Delgado, J. D., Tomás-Balibrea, L.-M. J. I. T. o. S., Man,, & Cybernetics, P. C. (2005). Automatic system for quality-based classification of marble textures. 35(4), 488-497.
- Mercan, Ö. B. (2020). Deep Learning based Colorimetric Classification of Glucose with Au-Ag nanoparticles using Smartphone. Paper presented at the 2020 Medical Technologies Congress (TIPTEKNO).
- Mercan, Ö. B., Doğan, V., & Kılıç, V. (2020). Time Series Analysis based Machine Learning Classification for Blood Sugar Levels. Paper presented at the 2020 Medical Technologies Congress (TIPTEKNO).
- Mercan, Ö. B., & Kılıç, V. (2020). Fuzzy classifier based colorimetric quantification using a smartphone. Paper presented at the International Conference on Intelligent and Fuzzy Systems.
- Mercan, Ö. B., Kılıç, V., & Şen, M. (2021). Machine learning-based colorimetric determination of glucose in artificial saliva with different reagents using a smartphone coupled μPAD. J Sensors Actuators B: Chemical, 329, 129037.
- Mutlu, A. Y., & Kılıç, V. (2018). Machine learning based smartphone spectrometer for harmful dyes detection in water. Paper presented at the 2018 26th Signal Processing and Communications Applications Conference (SIU).
- Pan, S. J., & Yang, Q. (2009). A survey on transfer learning. IEEE Transactions on Knowledge Data Engineering, 22(10), 1345-1359.
- Pençe, İ., & Çeşmeli, M. Ş. (2019). Deep learning in marble slabs classification. J Scientific Journal of Mehmet Akif Ersoy University, 2(1), 21-26.
- Selver, M. A., Akay, O., Alim, F., Bardakçı, S., & Ölmez, M. (2011). An automated industrial conveyor belt system using image processing and hierarchical clustering for classifying marble slabs. J Robotics Computer-Integrated Manufacturing, 27(1), 164-176.
- Shorten, C., & Khoshgoftaar, T. M. (2019). A survey on image data augmentation for deep learning. J Journal of Big Data, 6(1), 1-48.
- Şişeci, M., & Çetişli, B. (2012). Traverten plaka taşlarda sınıfların K-ortalamalar ve bulanık C-ortalamalar kümeleme yöntemleri ile belirlenmesi. J Süleyman Demirel Üniversitesi Fen Bilimleri Enstitüsü Dergisi, 16(3), 238-247.
- Umut, K., Yılmaz, A., & Dikmen, Y. (2019). Sağlık alanında kullanılan derin öğrenme yöntemleri. J Avrupa Bilim ve Teknoloji Dergisi(16), 792-808.
- Yin, J.-f., Bai, Q., & Zhang, B. (2018). Methods for detection of subsurface damage: a review. J Chinese Journal of Mechanical Engineering, 31(1), 1-14.
Deep Learning Based Automated Classification of Marble Surfaces
Yıl 2021,
Sayı: 26 - Ejosat Özel Sayı 2021 (HORA), 73 - 77, 31.07.2021
Mert Öktem
,
Şahin Alp Akosman
,
Özge Taylan Moral
,
Volkan Kılıç
Öz
The demand for marble has increased gradually in recent years with the increasing use of natural stones in architecture and decoration.
In order to meet the rising demand, producers must increase the efficiency of their marble production processes as well as increase their capacity. Production speed and efficiency decrease due to human-induced errors in marble classification, which is one of the marble production processes. In this study, as a solution to the problem of misclassification of marbles, an artificial intelligence supported system that classifies marble types with different colors and textures with high performance is proposed. In the proposed system, 12 convolutional neural network architectures were employed using transfer learning and deep learning methods to classify 516 marble images of 5 different marble types. As a result of the training with the augmented dataset, 96.07% classification accuracy was achieved with the VGG-16 architecture using transfer learning. Unlike similar studies, the proposed system has been integrated with our custom-designed interface. Thus, it is aimed to contribute to the classification of marbles which leads to less human-induced production issues.
Kaynakça
- Benavente, N., & Pina, P. (2009). Morphological segmentation and classification of marble textures at macroscopical scale. J Computers geosciences, 35(6), 1194-1204.
- Buduma, N., & Locascio, N. (2017). Fundamentals of deep learning: Designing next-generation machine intelligence algorithms: " O'Reilly Media, Inc.".
- Cheung, K. S. (2006). Modelling and analysis of manufacturing systems using augmented marked graphs. J Information Technology Control, 35(1).
- Ferreira, A., & Giraldi, G. (2017). Convolutional Neural Network approaches to granite tiles classification. J Expert Systems with Applications, 84, 1-11.
- Fırıldak, K., & Talu, M. F. (2019). Evrişimsel Sinir Ağlarında Kullanılan Transfer Öğrenme Yaklaşımlarının İncelenmesi. J Bilgisayar Bilimleri, 4(2), 88-95.
- KardanMoghaddama, H., Rajaeib, A., & Moghaddam, H. K. (2018). Marble slabs classification system based on image processing (ark marble mine in Birjand). J Civil Engineering Journal, 4(1).
- Kurt, F. (2018). Evrişimli Sinir Ağlarında Hiper Parametrelerin Etkisinin İncelenmesi. Hacettepe Üniversitesi Fen Bilimleri Enstitüsü,
- López, M., Martínez, J., Matías, J. M., Taboada, J., & Vilán, J. A. (2010). Functional classification of ornamental stone using machine learning techniques. Journal of Computational Applied Mathematics, 234(4), 1338-1345.
- Martínez-Alajarín, J., Luis-Delgado, J. D., Tomás-Balibrea, L.-M. J. I. T. o. S., Man,, & Cybernetics, P. C. (2005). Automatic system for quality-based classification of marble textures. 35(4), 488-497.
- Mercan, Ö. B. (2020). Deep Learning based Colorimetric Classification of Glucose with Au-Ag nanoparticles using Smartphone. Paper presented at the 2020 Medical Technologies Congress (TIPTEKNO).
- Mercan, Ö. B., Doğan, V., & Kılıç, V. (2020). Time Series Analysis based Machine Learning Classification for Blood Sugar Levels. Paper presented at the 2020 Medical Technologies Congress (TIPTEKNO).
- Mercan, Ö. B., & Kılıç, V. (2020). Fuzzy classifier based colorimetric quantification using a smartphone. Paper presented at the International Conference on Intelligent and Fuzzy Systems.
- Mercan, Ö. B., Kılıç, V., & Şen, M. (2021). Machine learning-based colorimetric determination of glucose in artificial saliva with different reagents using a smartphone coupled μPAD. J Sensors Actuators B: Chemical, 329, 129037.
- Mutlu, A. Y., & Kılıç, V. (2018). Machine learning based smartphone spectrometer for harmful dyes detection in water. Paper presented at the 2018 26th Signal Processing and Communications Applications Conference (SIU).
- Pan, S. J., & Yang, Q. (2009). A survey on transfer learning. IEEE Transactions on Knowledge Data Engineering, 22(10), 1345-1359.
- Pençe, İ., & Çeşmeli, M. Ş. (2019). Deep learning in marble slabs classification. J Scientific Journal of Mehmet Akif Ersoy University, 2(1), 21-26.
- Selver, M. A., Akay, O., Alim, F., Bardakçı, S., & Ölmez, M. (2011). An automated industrial conveyor belt system using image processing and hierarchical clustering for classifying marble slabs. J Robotics Computer-Integrated Manufacturing, 27(1), 164-176.
- Shorten, C., & Khoshgoftaar, T. M. (2019). A survey on image data augmentation for deep learning. J Journal of Big Data, 6(1), 1-48.
- Şişeci, M., & Çetişli, B. (2012). Traverten plaka taşlarda sınıfların K-ortalamalar ve bulanık C-ortalamalar kümeleme yöntemleri ile belirlenmesi. J Süleyman Demirel Üniversitesi Fen Bilimleri Enstitüsü Dergisi, 16(3), 238-247.
- Umut, K., Yılmaz, A., & Dikmen, Y. (2019). Sağlık alanında kullanılan derin öğrenme yöntemleri. J Avrupa Bilim ve Teknoloji Dergisi(16), 792-808.
- Yin, J.-f., Bai, Q., & Zhang, B. (2018). Methods for detection of subsurface damage: a review. J Chinese Journal of Mechanical Engineering, 31(1), 1-14.