MARBLE CLASSIFICATION USING DEEP NEURAL NETWORKS

Abstract

Deep learning, which has been described as the processing and interpretation of data, is now widely used. In this study, deep neural networks are used for the classification of marbles which can be used in the industry. For this purpose most used marbles images were obtained from companies in Turkey and 28-class dataset was created. Then VGG16, ResNet and LeNet models were trained on this dataset. Data augmentation was performed to have class balance. To evaluate the models performance accuracy metric is used. In the VGG16 model, fine tunning was applied and %97 accuracy was achieved. In experimental studies, models were trained with different parameter settings. The performances of the models are given comparatively. The fact that both new dataset and deep neural networks are used for the first time in marble classification are among the positive aspects of this study. It is planned to integrate the models produced in the future studies into mobile based expert systems.

Keywords

• Marble Classification,Deep Neural Networks,VGG16, ResNet

References

1. [1]S. Yalçın, T. Uyanık, Dünya mermer ticaretinde Türkiye’nin yeri, Türkiye III. Mermer Sempozyumu(2001) pp.397-416, Afyon.
2. [2]M. K. Gökay, I. B. Gundogdu, Color identification of some Turkish marbles. Construction and Building Materials, (2008), 22(7), 1342-1349.
3. [3]TURKSTAT, Turkey Marble Export, (2016).
4. [4]F. Bianconi, E. González, A. Fernández, S. A. Saetta, Automatic classification of granite tiles through colour and texture features. Expert Systems with Applications, (2012), 39(12), 11212-11218.
5. [5]V. G. Hernández, P. C. Perez, L. G. G. Pérez, L. M. T. Balibrea, H. P. Pina, Traditional and neural networks algorithms: applications to the inspection of marble slab. In Systems, Man and Cybernetics, (1995), Intelligent Systems for the 21st Century., IEEE International Conference on ,Vol. 5, pp. 3960-3965 IEEE.
6. [6]J. Martinez-Alajarin, Supervised classification of marble textures using support vector machines. Electronics Letters, (2004), 40(11), 664-666.
7. [7]L. Delgado, J. Dario, T. Balibrea, L. Manuel, M. C. D. V. Alajarín, J. de la Cruz, Automatic system for quality-based classification of marble textures, (2005).
8. [8]J. Martinez-Alajarin, J. D. Luis-Delgado and L. M. Tomas-Balibrea, Automatic system for quality-based classification of marble textures, in IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), (2005),vol. 35, no. 4, pp. 488-497, doi: 10.1109/TSMCC.2004.843236

9. [9]M. A. Selver, O. Akay, E. Ardali, A. Bahad, O. Onal, G. Ozden, Cascaded and hierarchical neural networks for classifying surface images of marble slabs. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), (2009), 39(4), 426-439.
10. [10]H. Doğan, O. Akay, Using AdaBoost classifiers in a hierarchical framework for classifying surface images of marble slabs. Expert Systems with Applications, (2010) ,37(12), 8814-8821.
11. [11]M. López, J. Martínez, J. M. Matías, J. Taboada, J. A. Vilán, Functional classification of ornamental stone using machine learning techniques. Journal of computational and applied mathematics, (2010), 234(4), 1338-1345.
12. [12]C. Topalova, A. Tzokev, Adaptive marble plate classification system based on neural network and Plc Implementation, Annals of DAAAM & Proceedings (2011).
13. [13]A. Krizhevsky, I. Sutskever, G. E. Hinton, ImageNet classification with deep convolutional neural networks. In Proceedings of the 25th International Conference on Neural Information Processing Systems, (2012),Volume 1 (NIPS'12), Vol. 1. Curran Associates Inc., USA, 1097-1105.
14. [14]Y. LeCun, Generalization and network design strategies. Technical Report CRG-TR-89-4, Department of Computer Science, University of Toronto, (1989).
15. [15]Kim, Y. Convolutional neural networks for sentence classification. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), (2014), pp. 1746–1751, Doha, Qatar. Association for Computational Linguistics.
16. [16]N. Benavente, P. Pina, Morphological segmentation and classification of marble textures at macroscopical scale, Computers &Geosciences, (2009)Volume 35, Issue 6, ,pp. 1194-1204,ISSN 0098-3004, https://doi.org/10.1016/j.cageo.2008.04.008.
17. [17]O. Akkoyun, An evaluation of image processing methods applied to marble quality classification, 2nd International Conference on Computer Technology and Development, Cairo, (2010), pp. 158-162. doi: 10.1109/ICCTD.2010.5646128
18. [18]M. A. Selver, O. Akay, F. Alim, S. Bardakçı, M. Ölmez, An automated industrial conveyor belt system using image processing and hierarchical clustering for classifying marble slabs, Robotics and Computer-Integrated Manufacturing,(2011)Volume 27, Issue 1, pp. 164-176,ISSN 0736-5845,https://doi.org/10.1016/j.rcim.2010.07.004.
19. [19]A. Ferreira, G. Giraldi, Convolutional Neural Network approaches to granite tiles classification, Expert Systems with Applications,Volume 84, (2017), pp. 1-11, ISSN 0957-4174, https://doi.org/10.1016/j.eswa.2017.04.053.
20. [20]A. Rosebrock, Deep learning for computer vision, (2017), PyImageSearch.
21. [21]I. Goodfellow, Y. Bengio, A. Courville, Deep Learning. http://www.deeplearningbook.org. MIT Press, (2016).
22. [22]Y. LeCun, L. Bottou, Y. Bengio, P. Haffner, Gradient-based learning applied to document recognition, in Proceedings of the IEEE, (1998) vol. 86, no. 11, pp. 2278-2324,
23. [23]Karen Simonyan and Andrew Zisserman, Very deep convolutional networks for large-scale image recognition, In: CoRR abs/1409.1556 (2014). URL: http://arxiv.org/abs/1409.1556
24. [24]K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, CoRR, (2015), abs/1512.03385.
25. [25]C. Szegedy et al., Going deeper with convolutions, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, (2015), pp. 1-9.
26. [26]OpenCV, (2019),https://opencv.org/
27. [27]Scikit-Learn Documentation,(2019), https://scikit-learn.org/stable/modules/generated/sklearn.metrics.classification_report.html