IRON ORE CHARACTERIZATION BY COMPUTER VISION / CARACTERIZAÇÃO DE MINÉRIO DE FERRO POR VISÃO COMPUTACIONAL
AUTOR(ES)
Marcio André Dell Aglio Frick
DATA DE PUBLICAÇÃO
2008
RESUMO
Ore classification is useful for understanding and controlling industrial beneficiation processes. The present work contributes to the developement of a computer vision system for automated classification of iron ores by image analysis of optical micrographs. For this purpose, morphological feature extraction algorithms were implemented and feature based classification algorithms were developed. These methods were successfully applied to the classification of hematite grains into four classes determined by their shape (lamellar or granular) and porosity (porous and compact) as characterized by just four features, namely, circularity, aspect ratio, fiber ratio and porosity.
ASSUNTO(S)
minério de ferro reconhecimento de padrões visão computacional computer vision classificação de minérios engenharia de producao pattern recognition, iron ore ore classification
ACESSO AO ARTIGO
http://coralx.ufsm.br/tede/tde_busca/arquivo.php?codArquivo=2225Documentos Relacionados
- Caracterização de rejeitos de minério de ferro para uso em pavimentação
- AUTOMATIC QUANTIFICATION OF METALLIC IRON IN SELF-REDUCING IRON ORE BRIQUETTES BY DIGITAL MICROSCOPY
- Métodos fotométricos para visão computacional
- Certification reference material of iron ore by interlaboratory program
- Iron ore supply chain: modeling and simulation.