A randomized algorithm for natural object colorization

Natural objects often contain vivid color distribution with wide variety of colors. Conventional colorization techniques, on the other hand, produce colors that are relatively flat with little color variation. In this paper, we introduce a randomized algorithm which considers not only the value of t...

Full description

Saved in:
Bibliographic Details
Published in:Computer graphics forum Vol. 33; no. 2; pp. 205 - 214
Main Authors: Jin, Sou-Young, Choi, Ho-Jin, Tai, Yu-Wing
Format: Journal Article
Language:English
Published: Oxford Blackwell Publishing Ltd 01.05.2014
Subjects:
Algorithms
Analysis
Categories and Subject Descriptors (according to ACM CCS)
Color
Colorization
Computer graphics
Consistency
Correlation
Correlation analysis
Histograms
I.3.8 [Computer Graphics]: Applications
Pixels
Studies
ISSN:0167-7055, 1467-8659
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Natural objects often contain vivid color distribution with wide variety of colors. Conventional colorization techniques, on the other hand, produce colors that are relatively flat with little color variation. In this paper, we introduce a randomized algorithm which considers not only the value of target color but also the distribution of target color. In essence, our algorithm paints a color distribution to a region which synthesizes color distribution of a natural object. Our approach models the correlation between intensity and color in HSV color space in terms of H – S, H – V and S – V joint histogram. During the colorization process, we randomly swap and reassign color of a pixel to minimize a cost function that measures color consistency to its neighborhood and intensity‐to‐color correlation captured in the joint histogram. We tested our algorithm extensively on many natural objects and our user study confirms that our results are more vivid and natural compared to results from previous techniques.
Bibliography:istex:DB9E56AA353B576F35344BE4393EFF3553E1B45D
ArticleID:CGF12294
ark:/67375/WNG-NJ5H72R8-F
Supporting Information
is excluded in the Graph cut implementation.
S
–
Color labels in Hue channel and Saturation channel are solved individually and the nonlocal neighboring term in Equation
http://vision.middlebury.edu/MRF/
4
log
We use another color image as an example image because it is closer to practical scenarios.
channel is selected since it captures grayscale with
0.
is a common method to convert an arg max probability problem into an arg min energy minimization problem
We use the middlebury MRF library for the Graph cut implementation
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ObjectType-Article-2
content type line 23
ISSN:0167-7055
1467-8659
DOI:10.1111/cgf.12294