SciELO - Scientific Electronic Library Online

 
vol.72 número146CONVERSIÓN DE DIAGRAMAS DE PROCESOS EN DIAGRAMAS DE CASOS DE USO USANDO AToM³ índice de autoresíndice de materiabúsqueda de artículos
Home Pagelista alfabética de revistas  

Servicios Personalizados

Revista

Articulo

Indicadores

Links relacionados

  • En proceso de indezaciónCitado por Google
  • No hay articulos similaresSimilares en SciELO
  • En proceso de indezaciónSimilares en Google

Compartir


DYNA

versión impresa ISSN 0012-7353versión On-line ISSN 2346-2183

Resumen

LOPEZ CARVAJAL, JAIME  y  BRANCH BEDOYA, JOHN WILLIAN. COMPARISON OF MODELS OF AUTOMATIC CLASSIFICATION OF TEXTURAL PATTERNS OF MINERAL PRESENTS IN COLOMBIAN COALS. Dyna rev.fac.nac.minas [online]. 2005, vol.72, n.146, pp.115-124. ISSN 0012-7353.

The automatic classification of objects is a very interesting approach under several problem domains. This paper outlines some results obtained under different classification models to categorize textural patterns of minerals using real digital images. The data set used was characterized by a small size and noise presence. The implemented models were the Bayesian classifier, Neural Network (2-5-1), Support Vector Machine, decision tree and 3-nearest neighbours. The results after applying crossed validation show that the Bayesian model (84%) proved better predictive capacity than the others, mainly due to its noise robustness behaviour. The Neuronal Network (68%) and the SVM (67%) gave promising results, because they could be improved increasing the data amount used, while the decision tree (55%) and k-NN (54%) did not seem to be adequate for this problem, because of their sensibility to noise.

Palabras clave : Classification; Digital Images; texture; coal minerals.

        · resumen en Español     · texto en Español     · Español ( pdf )

 

Creative Commons License Todo el contenido de esta revista, excepto dónde está identificado, está bajo una Licencia Creative Commons