Minerals Identification through Convolutional Neural Networks: a comparative study between Artificial Intelligence and the Human Visual System
Abstract
Mineral identification is extremely necessary for modern geology, especially when dealing with specific methods of geochronology and extraction of geological information. This process can be time consuming due to human evaluation in identification. In this way, this paper proposes the creation of a Convolutional Neural Network using microscopic images to identify Apatites, Quartz and Zircons, thus reducing manual resources and errors in this proccess. Identification tests with volunteers were carried out, comparing the results obtained by computer. In the end, the capacity of the Neural Networks of identifying minerals is verified, achieving results superior to human efforts and accuracy above 90%.
Keywords:
minerais, redes neurais convolucionais, classification
References
Bayka, N. and Yılmaz, N. (2010). Mineral identification using color spaces and artificial neural networks. Computers Geosciences, 36.
Borji, A. and Itti, L. (2014). Human vs. computer in scene and object recognition. 2014 IEEE Conference on Computer Vision and Pattern Recognition.
Bruand, E., Storey, C., and Fowler, M. (2014). Accessory mineral chemistry of high ba sr granites from northern scotland: Constraints on petrogenesis and records of wholerock signature. Journal of Petrology, 55.
Franco, A. O. B. (2006). Termocronologia por traços de fissão em apatitas na região do arco de ponta grossa, entre os alinhamentos de guapiara e são jeronimo-curiúva. Master’s thesis, Universidade Estadual Paulista, Rio Claro Brasil.
Izadi, H., Sadri, J., and Mahdokht, B. (2017). An intelligent system for mineral identification in thin sections based on a cascade approach. Computers & Geoscience.
Jain, A. K., Mao, J., and Mohiuddin, K. (1996). Artificial neural networks: A tutorial. Computer, (3).
Klein, C. and Dutrow, B. (2009). Manual de ciência dos minerais. Bookman Editora.
Krizhevsky, A., Sutskever, I., and Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems.
Maitre, J., Bouchard, K., and Bedard, P. (2019). Mineral grains recognition using computer vision and machine learning. Computers Geosciences, 27.
Miynarczuk, M., Górszczyk, A., and Slipek, B. (2013). The application of pattern recognition in the automatic clasffication on microscopic rock images. Computers & Geoscience.
Pereira, R. and Porto, F. (2019). Deep learning application for plant classification on unbalanced training set. In Anais do XIII Brazilian e-Science Workshop. SBC.
Thompson, S., Fueten, F., and Bockus, D. (2001). Mineral identification using artificial neural networks and the rotating polarizer stage. Computers Geosciences, 27.
Tokui, S., Oono, K., Hido, S., and Clayton, J. (2015). Chainer: a next-generation open source framework for deep learning. In Proceedings of workshop on machine learning systems (LearningSys) in the twenty-ninth annual conference on neural information processing systems (NIPS), pages 1–6.
Zhang, M. (2017). Raman Study of the Crystalline-to-Amorphous State in Alpha- Decay–Damaged Materials.
Borji, A. and Itti, L. (2014). Human vs. computer in scene and object recognition. 2014 IEEE Conference on Computer Vision and Pattern Recognition.
Bruand, E., Storey, C., and Fowler, M. (2014). Accessory mineral chemistry of high ba sr granites from northern scotland: Constraints on petrogenesis and records of wholerock signature. Journal of Petrology, 55.
Franco, A. O. B. (2006). Termocronologia por traços de fissão em apatitas na região do arco de ponta grossa, entre os alinhamentos de guapiara e são jeronimo-curiúva. Master’s thesis, Universidade Estadual Paulista, Rio Claro Brasil.
Izadi, H., Sadri, J., and Mahdokht, B. (2017). An intelligent system for mineral identification in thin sections based on a cascade approach. Computers & Geoscience.
Jain, A. K., Mao, J., and Mohiuddin, K. (1996). Artificial neural networks: A tutorial. Computer, (3).
Klein, C. and Dutrow, B. (2009). Manual de ciência dos minerais. Bookman Editora.
Krizhevsky, A., Sutskever, I., and Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems.
Maitre, J., Bouchard, K., and Bedard, P. (2019). Mineral grains recognition using computer vision and machine learning. Computers Geosciences, 27.
Miynarczuk, M., Górszczyk, A., and Slipek, B. (2013). The application of pattern recognition in the automatic clasffication on microscopic rock images. Computers & Geoscience.
Pereira, R. and Porto, F. (2019). Deep learning application for plant classification on unbalanced training set. In Anais do XIII Brazilian e-Science Workshop. SBC.
Thompson, S., Fueten, F., and Bockus, D. (2001). Mineral identification using artificial neural networks and the rotating polarizer stage. Computers Geosciences, 27.
Tokui, S., Oono, K., Hido, S., and Clayton, J. (2015). Chainer: a next-generation open source framework for deep learning. In Proceedings of workshop on machine learning systems (LearningSys) in the twenty-ninth annual conference on neural information processing systems (NIPS), pages 1–6.
Zhang, M. (2017). Raman Study of the Crystalline-to-Amorphous State in Alpha- Decay–Damaged Materials.
Published
2020-06-30
How to Cite
ARINOS, Victor Félix; VENTURA, Thiago Meirelles; ARINOS, Natali Félix; RUIZ, Amarildo Salina.
Minerals Identification through Convolutional Neural Networks: a comparative study between Artificial Intelligence and the Human Visual System. In: BRAZILIAN E-SCIENCE WORKSHOP (BRESCI), 14. , 2020, Cuiabá.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2020
.
p. 105-112.
ISSN 2763-8774.
DOI: https://doi.org/10.5753/bresci.2020.11188.
