Global Distribution Adjustment and Nonlinear Feature Transformation for Automatic Colorization
Automatic colorization is generally classified into two groups: propagation-based methods and reference-based methods. In reference-based automatic colorization methods, color image(s) are used as reference(s) to reconstruct original color of a gray target image. The most important task here is to f...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Hindawi Limited
2018-01-01
|
Series: | Advances in Multimedia |
Online Access: | http://dx.doi.org/10.1155/2018/1504691 |
id |
doaj-03678e8c59fc43aa81dad0eee02858fd |
---|---|
record_format |
Article |
spelling |
doaj-03678e8c59fc43aa81dad0eee02858fd2020-11-25T03:28:02ZengHindawi LimitedAdvances in Multimedia1687-56801687-56992018-01-01201810.1155/2018/15046911504691Global Distribution Adjustment and Nonlinear Feature Transformation for Automatic ColorizationTerumasa Aoki0Van Nguyen1New Industry Hatchery Center (NICHe), Tohoku University, Sendai 9808579, JapanGraduate School of Information Science (GSIS), Tohoku University, Sendai 9808579, JapanAutomatic colorization is generally classified into two groups: propagation-based methods and reference-based methods. In reference-based automatic colorization methods, color image(s) are used as reference(s) to reconstruct original color of a gray target image. The most important task here is to find the best matching pairs for all pixels between reference and target images in order to transfer color information from reference to target pixels. A lot of attractive local feature-based image matching methods have already been developed for the last two decades. Unfortunately, as far as we know, there are no optimal matching methods for automatic colorization because the requirements for pixel matching in automatic colorization are wholly different from those for traditional image matching. To design an efficient matching algorithm for automatic colorization, clustering pixel with low computational cost and generating descriptive feature vector are the most important challenges to be solved. In this paper, we present a novel method to address these two problems. In particular, our work concentrates on solving the second problem (designing a descriptive feature vector); namely, we will discuss how to learn a descriptive texture feature using scaled sparse texture feature combining with a nonlinear transformation to construct an optimal feature descriptor. Our experimental results show our proposed method outperforms the state-of-the-art methods in terms of robustness for color reconstruction for automatic colorization applications.http://dx.doi.org/10.1155/2018/1504691 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Terumasa Aoki Van Nguyen |
spellingShingle |
Terumasa Aoki Van Nguyen Global Distribution Adjustment and Nonlinear Feature Transformation for Automatic Colorization Advances in Multimedia |
author_facet |
Terumasa Aoki Van Nguyen |
author_sort |
Terumasa Aoki |
title |
Global Distribution Adjustment and Nonlinear Feature Transformation for Automatic Colorization |
title_short |
Global Distribution Adjustment and Nonlinear Feature Transformation for Automatic Colorization |
title_full |
Global Distribution Adjustment and Nonlinear Feature Transformation for Automatic Colorization |
title_fullStr |
Global Distribution Adjustment and Nonlinear Feature Transformation for Automatic Colorization |
title_full_unstemmed |
Global Distribution Adjustment and Nonlinear Feature Transformation for Automatic Colorization |
title_sort |
global distribution adjustment and nonlinear feature transformation for automatic colorization |
publisher |
Hindawi Limited |
series |
Advances in Multimedia |
issn |
1687-5680 1687-5699 |
publishDate |
2018-01-01 |
description |
Automatic colorization is generally classified into two groups: propagation-based methods and reference-based methods. In reference-based automatic colorization methods, color image(s) are used as reference(s) to reconstruct original color of a gray target image. The most important task here is to find the best matching pairs for all pixels between reference and target images in order to transfer color information from reference to target pixels. A lot of attractive local feature-based image matching methods have already been developed for the last two decades. Unfortunately, as far as we know, there are no optimal matching methods for automatic colorization because the requirements for pixel matching in automatic colorization are wholly different from those for traditional image matching. To design an efficient matching algorithm for automatic colorization, clustering pixel with low computational cost and generating descriptive feature vector are the most important challenges to be solved. In this paper, we present a novel method to address these two problems. In particular, our work concentrates on solving the second problem (designing a descriptive feature vector); namely, we will discuss how to learn a descriptive texture feature using scaled sparse texture feature combining with a nonlinear transformation to construct an optimal feature descriptor. Our experimental results show our proposed method outperforms the state-of-the-art methods in terms of robustness for color reconstruction for automatic colorization applications. |
url |
http://dx.doi.org/10.1155/2018/1504691 |
work_keys_str_mv |
AT terumasaaoki globaldistributionadjustmentandnonlinearfeaturetransformationforautomaticcolorization AT vannguyen globaldistributionadjustmentandnonlinearfeaturetransformationforautomaticcolorization |
_version_ |
1724585731161063424 |