首页    期刊浏览 2024年12月05日 星期四
登录注册

文章基本信息

  • 标题:Quantitative Ore Texture Analysis with Convolutional Neural Networks
  • 本地全文:下载
  • 作者:Y. Fu ; C. Aldrich
  • 期刊名称:IFAC PapersOnLine
  • 印刷版ISSN:2405-8963
  • 出版年度:2019
  • 卷号:52
  • 期号:14
  • 页码:99-104
  • DOI:10.1016/j.ifacol.2019.09.171
  • 语种:English
  • 出版社:Elsevier
  • 摘要:Liberation of valuable minerals from their gangue matrices depends on the physical properties of the ore, as well as the features of the process used to extract these minerals from the rock particulates. Despite the fact that the texture of the ore is an important predictor of liberation in an ore system, it is only recently that quantitative descriptors of the texture have been included in liberation models. These descriptors can be obtained in a variety of ways, but a general methodology has not yet been established. In this study, recent advances in quantitative ore texture analysis are reviewed and the feasibility of using state-of-the-art computer vision technology based on convolutional neural networks for ore texture analysis is considered.
  • 关键词:Keywordsore texturemultivariate image analysislocal binary patternsconvolutional neural networkdeep learningResNetmineral processing
国家哲学社会科学文献中心版权所有