Share Email Print

Proceedings Paper

Object-to-object color mapping by image segmentation
Author(s): Hiroaki Kotera; Hung-Shing Chen; Tetsuro Morimoto
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

An object-to-object color mapping strategy depending on the image color contents is proposed. Pictorial color image is segmented into different object areas with clustered color distributions. Euclidian or Mahalanobis color distance measures, and Bayesian decision rule based on maximum likelihood principle, are introduced to the image segmentation. After the image segmentation each segmented pixels are projected onto principal component space by Hotelling transform and the color mapping s are performed for the principal components to be matched in between the individual objects of original and printed images. Experimental results in automatic color correction for inkjet prints are reported. The paper discusses on the color correction effects by PCA matching and reproduction errors in relation to the segmentation methods.

Paper Details

Date Published: 22 December 1998
PDF: 10 pages
Proc. SPIE 3648, Color Imaging: Device-Independent Color, Color Hardcopy, and Graphic Arts IV, (22 December 1998); doi: 10.1117/12.334552
Show Author Affiliations
Hiroaki Kotera, Chiba Univ. (Japan)
Hung-Shing Chen, Chiba Univ. (Japan)
Tetsuro Morimoto, Chiba Univ. (Japan)

Published in SPIE Proceedings Vol. 3648:
Color Imaging: Device-Independent Color, Color Hardcopy, and Graphic Arts IV
Giordano B. Beretta; Reiner Eschbach, Editor(s)

© SPIE. Terms of Use
Back to Top