Back to articles
Volume: 14 | Article ID: art00076_1
Object to Object Color Matchings By Image Clustering
  DOI :  10.2352/ISSN.2169-4451.1998.14.1.art00076_1  Published OnlineJanuary 1998

Object to object color matching strategy depending on the image contents is proposed. Pictorial color image is classified into different object areas with clustered color distributions. Euclidian or Mahalanobis color distance measures, and maximum likelihood method based on Bayesian decision rule, are introduced to the classification. After the objects' classification, each clustered pixels are projected onto principal component space by Hotelling transform and the color mappings are performed for the principal components to be matched in between the individual objects of original and printed images.

Subject Areas :
Views 5
Downloads 0
 articleview.views 5
 articleview.downloads 0
  Cite this article 

Hiroaki Kotera, Teturo Morimoto, Ryoichi Saito, "Object to Object Color Matchings By Image Clusteringin Proc. IS&T Int'l Conf. on Digital Printing Technologies (NIP14),  1998,  pp 310 - 314,

 Copy citation
  Copyright statement 
Copyright © Society for Imaging Science and Technology 1998
NIP & Digital Fabrication Conference
nip digi fabric conf
Society of Imaging Science and Technology
7003 Kilworth Lane, Springfield, VA 22151, USA