Application of Artificial Intelligence for Mineral Identification Using Thin-Section Images
DOI:
https://doi.org/10.66778/CTI.v02n01.02Palabras clave:
Transferencia de Aprendizaje, ResNet50, HiperparámetrosResumen
This article presents a computer vision approach for the automated classification of minerals from microscopic images, a task of significant relevance in geological and mining applications. The proposed method employs the ResNet50 architecture within a Transfer Learning framework and is optimized through a rigorous hyperparameter search. The final model, trained using a batch size of 8 and an L2 regularization factor of 1.0×10-⁵, achieved a validation loss of 0.0447 and a validation accuracy of 98.35% across ten mineral classes. The results indicate a superior generalization capability compared to baseline models, establishing the proposed classifier as a reliable tool for laboratory sample analysis.
Descargas
Referencias
Esteva, A., Kuprel, B., Novoa, R. A., Ko, J., Swetter, S. M., Blau, H. M., & Thrun, S. (2017).Dermatologist-level classi- fication of skin cancer with deep neural networks. Natu- re,542(7639),115–118.https://doi.org/10.1038/nature21056
Kamilaris, A., & Prenafeta-Boldú, F. X. (2018).Deep learning in agriculture: A survey. Computers and Electronics inAgriculture ,147,70–90.https ://do i.o rg/10.1016/j. compag.2018.02.016
Jahoda, R., Moudrý, V., & Müllerová, J. (2020).Deep learning for lithological mapping using remote sensing data. Remote Sensing, 12(10), 1620.https://doi.org/10.3390/rs12101620
Khaleque, A., Baran, R., & Islam, M. (2022).Deep learning- based mineral identification from petrographic images. Applied Computing and Geosciences, 14, 100084.https://doi. org/10.1016/j.acags.2022.100084
Hwang, J., Kim, H., & Lee, S. (2021).Automatic mineral classification using convolutional neural networks on petrographic thin-section images. Computers & Geosciences, 157, 104921.https://doi.org/10.1016/j.cageo.2021.104921
Lexa, J., Halouzka, R., & Martí, J. (2011).Volcanic evolution of the Central American Volcanic Arc. Geological Society, London, Special Publications, 361(1), 1–27.https://doi. org/10.1144/SP361.1
Montalvo, C., & Martí, J. (2013).Geological evolution of El Salvador volcanic regions. Journal of Volcanology and Geothermal Research, 258, 1–15.https://doi.org/10.1016/j. jvolgeores.2013.03.012
He, K., Zhang, X., Ren, S., & Sun, J. (2016).Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR),770–778.https://doi.org/10.1109/CVPR.2016.90
Descargas
Publicado
Número
Sección
Licencia
Derechos de autor 2026 Sofia Martínez; José Antonio Osorio Guandique , Balmore Quintanilla Barrera, Bladimir Díaz Campos, Nelly Lissette Henriquez Sanchez
Esta obra está bajo una licencia internacional Creative Commons Atribución-NoComercial 4.0.
