Paper Info
Title
Self-similarity-based image colorization
Abstract
In this work, we tackle the problem of coloring black-and-white images, which is image colorization. Existing image colorization algorithms can be categorized into two types: scribble-based colorization algorithms and example-based colorization algorithms. Differently, we propose a hybrid scheme that combines the advantages of both categories. Given the grayscale image to be colorized and a few color scribbles (or scattered color labels) as input, the proposed method manages to colorize the grayscale image with high quality. Similar to the mechanisms in example-based colorization methods, our algorithm firstly propagates chrominance information based on the assumption that similar image patches should have similar colors. Therefore colors of some pixels can be transferred from similar patches with known colors. After that, we apply scribble-based colorization algorithm to fully colorize the grayscale image, with different confidences assigned onto the transferred color labels. Experimental results show that, the proposed method effectively utilizes the known chrominance, and provides pleasant colorizations with very few user interventions.
Year
DOI
Venue
2014
10.1109/ICIP.2014.7025950
ICIP
Keywords
Field
DocType
grayscale image,hybrid scheme,colorization,chrominance information,self-similarity,image restoration,scribble-based colorization,image colorization,image patch,optimization,scattered color labels,black-and-white image color,non-local method,self similarity,image colour analysis
Scribble,Computer vision,Image colorization,Pattern recognition,Computer science,Chrominance,Artificial intelligence,Pixel,Image restoration,Self-similarity,Grayscale,Color image
Conference
ISSN
Citations 
PageRank 
1522-4880
5
0.41
References 
Authors
11
6
Name
Order
Citations
PageRank
Jiahao Pang114912.42
Oscar C. Au21592176.54
Yukihiko Yamashita311230.30
Yonggen Ling4163.63
Yuanfang Guo59518.21
Jin Zeng6102.54