Rock lithological classification using multi-scale Gabor features from sub-images, and voting with rock contour information
Published in International Journal of Mineral Processing, 2015
Recommended citation: Perez, C. A., Saravia, J. A., Navarro, C. F., Schulz, D. A., Aravena, C. M., & Galdames, F. J. (2015). Rock lithological classification using multi-scale Gabor features from sub-images and voting with rock contour information. International Journal of Mineral Processing, 144, 56–64. https://doi.org/10.1016/j.minpro.2015.09.015 https://doi.org/10.1016/j.minpro.2015.09.015
Developed a computer vision method for automated lithological classification in mining environments using video-based analysis of conveyor belt systems.
The approach combines multi-scale texture extraction using Gabor filters with support vector machine (SVM) classification, enabling robust recognition of rock types under real-world conditions.
The method achieved improvements in classification accuracy ranging from 8.3% to 26% compared to previous approaches, demonstrating its potential for optimizing grinding process control in mining operations.