Back
Colorization algorithm using probabilistic relaxation 

作成者 堀内, 隆彦
作成者 (ヨミ) ホリウチ, タカヒコ
作成者の別表記 Horiuchi, Takahiko
キーワード等 colorization, probabilistic relaxation, Markov property, grayscale image
日本十進分類法 (NDC) 141.2
内容 This paper presents a method of colorizing a black and white imagery based on the probabilistic relaxation algorithm. Since the colorization is an ill-posed problem, a user specifies a suitable color on each isolated pixel of an image as a prior information in this paper. Then other pixels in the image are colorized automatically. The colorizing process is done by assuming local Markov property on the images. By minimizing a total of RGB pixel-wise differences, the problem can be considered as a combinatorial optimization problem and it is solved by using the probabilistic relaxation. The proposed algorithm works very well when a few percent color pixels are knownwith confidence.
コンテンツの種類 雑誌掲載論文 Journal Article
DCMI資源タイプ text
ファイル形式 application/pdf, application/x-dvi
ハンドルURL http://mitizane.ll.chiba-u.jp/meta-bin/mt-pdetail.cgi?cd=00020925
DOI 10.1016/j.imavis.2003.08.004
掲載誌情報 Image and Vision Computing Vol.22 no.3 page.197-202 (20040301)
フルテキストへのリンク http://mitizane.ll.chiba-u.jp/metadb/up/CUS20040015/IVC2003.pdf, http://mitizane.ll.chiba-u.jp/metadb/up/green2005/2005THoriuchi.dvi
言語 英語
関連情報 (hasVersion) http://dx.doi.org/10.1016/j.imavis.2003.08.004


Total Access Count:

638 times.


Search
Related Materials in




colorization
probabilistic relaxation
Markov property
grayscale image