22 December 1998 Object-to-object color mapping by image segmentation
Author Affiliations +
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.
© (1998) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Hiroaki Kotera, Hiroaki Kotera, Hung-Shing Chen, Hung-Shing Chen, Tetsuro Morimoto, Tetsuro Morimoto, } "Object-to-object color mapping by image segmentation", Proc. SPIE 3648, Color Imaging: Device-Independent Color, Color Hardcopy, and Graphic Arts IV, (22 December 1998); doi: 10.1117/12.334552; https://doi.org/10.1117/12.334552
PROCEEDINGS
10 PAGES


SHARE
Back to Top