A Colorization Algorithm Based on Local MAP Estimation

DOI IR IR (HANDLE) 1 Citations

Search this article

Description

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 randomfield (MRF) is used for modeling a color image which is utilized as a prior for theMAP estimation. The MAP estimation problem for a whole image is decomposedinto local MAP estimation problems for each pixel. Using 0.6% of whole pixels asreferences, the proposed method produced pretty high quality color images with25.7 dB to 32.6 dB PSNR values for eight images.

Journal

Citations (1)*help

See more

Keywords

Details 詳細情報について

Report a problem

Back to top