Improvement on colorization accuracy by partitioning algorithm in CIELAB color space

Authors:
Tomohisa Takahama;Takahiko Horiuchi;Hiroaki Kotera
Affiliations:
Graduate School of Science and Technology, Chiba University, Chiba, Japan;Graduate School of Science and Technology, Chiba University, Chiba, Japan;Graduate School of Science and Technology, Chiba University, Chiba, Japan
Venue:
PCM'04 Proceedings of the 5th Pacific Rim Conference on Advances in Multimedia Information Processing - Volume Part II
Year:
2004

Citing 3
Cited 0

Digital image processing (2nd ed.)

Digital image processing (2nd ed.)
Transferring color to greyscale images

Proceedings of the 29th annual conference on Computer graphics and interactive techniques
Color Transfer between Images

IEEE Computer Graphics and Applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

Colorization is a computerized process that adds color to monochrome images. Since different colors may carry the same luminance in spite of differences in hue and/or saturation, the colorization is an ill-posed problem. In the previous studies, one of the authors has proposed a colorization algorithm by sawing seed colors and propagating them in RGB color space. However, there is an error propagation problem at edges. In this paper, we improve on colorization accuracy for monochrome images by setting partitions which can prevent color propagation at edges. Furthermore, we newly introduce a colorization technique in CIELAB color space, and more accurate colorization can be obtained. The performance is verified by experiments.