From Rocks to Pixels: A Protocol for Reproducible Mineral Imaging and its Applications in Machine Learning

Author:

Back Arnaud L.1ORCID,Bédard L. Paul1ORCID,Maitre Julien2,Bouchard Kévin2ORCID

Affiliation:

1. LabMaTer, Sciences de la Terre, Université du Québec à Chicoutimi, 555 Boulevard de l’Université, Chicoutimi, QC G7H 2B1, Canada

2. Department of Computer Sciences and Mathematics, Université du Québec à Chicoutimi, 555 Boulevard de l’Université, Chicoutimi, QC G7H 2B1, Canada

Abstract

Identifying minerals is essential for geology, mineral exploration, engineering, and environmental sciences. Recent advances in machine learning have illustrated its potential as a fast, cost-effective, and reliable tool for identifying minerals from photographs or photomicrographs. However, in the recent literature, few studies have been dedicated to image acquisition. Machine learning generally requires reproducible, high-quality data to perform complicated tasks such as mineral identification to avoid common pitfalls. In this paper, we propose a practical image acquisition protocol for optical microscopes. This protocol focuses on ensuring reproducibility and enhancing image quality. To favor reproducibility, we detail dealing with camera errors, using reference color gauges, and establishing experimental parameters such as the external light source and temperature. For image enhancement, we explain the importance of lighting and its impact on machine learning precision, selection of the objective, and white balance calibration. In addition, we trialed the protocol on heavy mineral concentrate from till samples (20 species) with a typical deep learning model and it revealed that minor lighting modification (<5% difference in one channel) significantly increased misclassification rates: kyanite from 6.4% to 24.9% and monazite from 6.5% to 42.9%.

Funder

Fonds de Recherche du Québec - Nature et Technologies

IOS Servives Géoscientifiques Inc.

Publisher

MDPI AG

Subject

Geology,Geotechnical Engineering and Engineering Geology

Reference31 articles.

1. The Application of Heavy Indicator Mineralogy in Mineral Exploration with Emphasis on Base Metal Indicators in Glaciated Metamorphic and Plutonic Terrains;Averill;Geol. Soc. Lond. Spec. Publ.,2001

2. Indicator Mineral and Surficial Geochemical Exploration Methods for Kimberlite in Glaciated Terrain; Examples from Canada;Goodfellow;Mineral Deposits of Canada: A Synthesis of Major Deposit-Types, District Metallogeny, the Evolution of Geological Provinces, and Exploration Methods,2007

3. The Effect of Phyllosilicate Minerals on Mineral Processing Industry;Ndlovu;Int. J. Miner. Process.,2013

4. Sulfide Oxidation Observed Using Micro-Raman Spectroscopy and Micro-X-Ray Diffraction: The Importance of Water/Rock Ratios and pH Conditions;Bril;Am. Mineral.,2010

5. Mineral Grains Recognition Using Computer Vision and Machine Learning;Maitre;Comput. Geosci.,2019

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3