A colorization algorithm based on local MAP estimation

Authors:
Hideki Noda;Jin Korekuni;Michiharu Niimi
Affiliations:
Department of Systems Innovation and Informatics, Kyushu Institute of Technology, 680-4 Kawazu, Iizuka 820-8502, Japan;Department of Electrical, Electronic and Computer Engineering, Kyushu Institute of Technology, 1-1 Sensui-cho, Tobata-ku, Kitakyushu 804-8550, Japan;Department of Systems Innovation and Informatics, Kyushu Institute of Technology, 680-4 Kawazu, Iizuka 820-8502, Japan
Venue:
Pattern Recognition
Year:
2006

Citing 3
Cited 1

Transferring color to greyscale images

Proceedings of the 29th annual conference on Computer graphics and interactive techniques
Colorization using optimization

ACM SIGGRAPH 2004 Papers
Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images

IEEE Transactions on Pattern Analysis and Machine Intelligence

Colorization in YCbCr color space and its application to JPEG images

Pattern Recognition

Quantified Score

Hi-index	0.01

Visualization

Abstract

This paper presents a colorization algorithm which adds color to monochrome images. In this paper, the colorization problem is formulated as the maximum a posteriori (MAP) estimation of a color image given a monochrome image. Markov random field (MRF) is used for modeling a color image which is utilized as a prior for the MAP estimation. The MAP estimation problem for a whole image is decomposed into local MAP estimation problems for each pixel. Using 0.6% of whole pixels as references, the proposed method produced pretty high quality color images with 25.7-32.6dB PSNR values for eight images.