Back to articles
Articles
Volume: 24 | Article ID: art00026
Image
Classification of painting techniques with color Run-Length Matrices
  DOI :  10.2352/ISSN.2169-2629.2017.32.157  Published OnlineNovember 2016
Abstract

In human and computer vision, the analysis of color and texture is primordial for object recognition and image classification. The analysis of color textures mainly contributes to the automatic classification in industrial images, satellite images, bio-medical images, or patrimonial images. The aim of this paper is to propose a new color statistical measure for texture analysis, based on color Run-Length Matrices (cRLM), associated to Principal Component Analysis (ACP) for paintings classification. The effectiveness of our approach is assessed by results of perfect classification in a same group of the attributes space of all the paintings of an artist. These results suggest that color Run-Length Matrices are a suitable basis for color texture analysis in numerous applications based upon color textured regions classification.

Subject Areas :
Views 1
Downloads 0
 articleview.views 1
 articleview.downloads 0
  Cite this article 

Alexandre Bony, "Classification of painting techniques with color Run-Length Matricesin Proc. IS&T 24th Color and Imaging Conf. ,  2016,  https://doi.org/10.2352/ISSN.2169-2629.2017.32.157

 Copy citation
  Copyright statement 
Copyright © Society for Imaging Science and Technology 2016
72010350
Color and Imaging Conference
color imaging conf
2166-9635
Society for Imaging Science and Technology