Optical Classification of Quartz Lascas by Artificial Neural Networks
- 21 November 2014
- journal article
- research article
- Published by Taylor & Francis in Mineral Processing and Extractive Metallurgy Review
- Vol. 36 (5) , 281-287
Abstract
A gradation method based on quartz lascas (lumps) transparency level is proposed. The samples were irradiated by transmitting light, and the images histograms were processed by artificial neural networks. Additionally, the results were compared to conventional classification methods, including density and visual analysis. The network designed with backpropagation architecture using 4 hidden layers of 10 neurons yielded to a relative error <24% in relation to manual classification, indicating a good agreement to the miners criteria. Furthermore, the implementation of competitive learning with 5 neurons resulted in correct discrimination of samples regarding their optical characteristics with a completely non-subjective approach.Keywords
Funding Information
- This work was supported in part by FAPESP, CNPq and CAPES. E.F. thanks the fellowship from FAPESP.
This publication has 16 references indexed in Scilit:
- Opacity measurements on quartz and its influence on silica glass propertiesInternational Journal of Mineral Processing, 2013
- Ore grade estimation by feature selection and voting using boundary detection in digital image analysisInternational Journal of Mineral Processing, 2011
- Mineral identification using color spaces and artificial neural networksComputers & Geosciences, 2010
- Direct Effects of UV-B Radiation on the Freshwater Heterotrophic NanoflagellateParaphysomonasspApplied and Environmental Microbiology, 2009
- A machine vision approach to on-line estimation of run-of-mine ore composition on conveyor beltsMinerals Engineering, 2007
- Growth of structure-controlled polycrystalline silicon ingots for solar cells by castingActa Materialia, 2006
- VisioRock, an integrated vision technology for advanced control of comminution circuitsMinerals Engineering, 2004
- Mineral identification using artificial neural networks and the rotating polarizer stageComputers & Geosciences, 2001
- Impurity Content Characterization of Brazilian Quartz LascasJapanese Journal of Applied Physics, 1991
- The self-organizing mapProceedings of the IEEE, 1990