Back to articles
Volume: 1 | Article ID: art00083
Classification of Color Colposcopic Images by Neural Networks
  DOI :  10.2352/CGIV.2002.1.1.art00083  Published OnlineJanuary 2002

This article presents colposcopic image classification based on color parameters used in a comparison study of different artificial neural networks and the knearest neighbors reference method. In this study, significant image data bases are used (617 images) from which two sets of parameters is extracted to characterize the attribute of color. More precisely, we select a set of color componants from color spaces based on data analysis and inner characteristics of different colposcopic image examinations. Experimental results show the feasibility of this study and the efficiency of the two sets of parameters since 90.9% of pink/red image set and 78% of brown/yellow image set have been correctly classified.

Subject Areas :
Views 4
Downloads 0
 articleview.views 4
 articleview.downloads 0
  Cite this article 

Isabelle Claude, Renaud Winzenrieth, Philippe Pouletaut, Jean-Charles Boulanger, "Classification of Color Colposcopic Images by Neural Networksin Proc. IS&T CGIV 2002 First European Conf. on Colour in Graphics, Imaging, and Vision,  2002,  pp 394 - 397,

 Copy citation
  Copyright statement 
Copyright © Society for Imaging Science and Technology 2002
Conference on Colour in Graphics, Imaging, and Vision
conf colour graph imag vis
Society of Imaging Science and Technology
7003 Kilworth Lane, Springfield, VA 22151, USA