A SIMPLE AND EFFICIENT COLORIZATION ALGORITHM USING MRF MODELING(International Workshop on Advanced Image Technology 2006)

概要

論文の詳細を見る
This paper presents an efficient colorization algorithm which produces color images from given monochrome images. Unlike previously proposed colorization methods, this paper formulates the colorization problem 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 priori information for the MAP estimation. The MAP estimation problem for a whole image is decomposed into local MAP estimation problems for each pixel, and then an efficient estimation method is derived for the local MAP estimation. Using 0.6% of whole pixels as references, the proposed method produced pretty high quality color images with 25.7dB to 32.5dB PSNR values for four standard images. Computation time to colorize one image of 256×256 pixel size was a few seconds.
社団法人電子情報通信学会の論文
2006-01-03