Color image demosaicing using progressive collaborative representation
In this paper, a progressive collaborative representation (PCR) framework is proposed that is able to incorporate any existing color image demosaicing method for further boosting its demosaicing performance. Our PCR consists of two phases: (i) offline training and (ii) online refinement. In phase (i...
Saved in:
Main Authors: | , , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2022
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/161038 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-161038 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1610382022-08-12T05:28:28Z Color image demosaicing using progressive collaborative representation Ni, Zhangkai Ma, Kai-Kuang Zeng, Huanqiang Zhong, Baojiang School of Electrical and Electronic Engineering Engineering::Electrical and electronic engineering Training Image Color Analysis In this paper, a progressive collaborative representation (PCR) framework is proposed that is able to incorporate any existing color image demosaicing method for further boosting its demosaicing performance. Our PCR consists of two phases: (i) offline training and (ii) online refinement. In phase (i), multiple training-and-refining stages will be performed. In each stage, a new dictionary will be established through the learning of a large number of feature-patch pairs, extracted from the demosaicked images of the current stage and their corresponding original full-color images. After training, a projection matrix will be generated and exploited to refine the current demosaicked image. The updated image with improved image quality will be used as the input for the next training-and-refining stage and performed the same processing likewise. At the end of phase (i), all the projection matrices generated as above-mentioned will be exploited in phase (ii) to conduct online demosaicked image refinement of the test image. Extensive simulations conducted on two commonly-used test datasets (i.e., the IMAX and Kodak) for evaluating the demosaicing algorithms have clearly demonstrated that our proposed PCR framework is able to constantly boost the performance of any image demosaicing method we experimented, in terms of the objective and subjective performance evaluations. Ministry of Education (MOE) This work supported by Ministry of Education, Singapore, under Grant AcRF TIER 1 2017-T1-002-110 and Grant TIER 2 2015-T2-2-114. 2022-08-12T05:28:28Z 2022-08-12T05:28:28Z 2020 Journal Article Ni, Z., Ma, K., Zeng, H. & Zhong, B. (2020). Color image demosaicing using progressive collaborative representation. IEEE Transactions On Image Processing, 29, 4952-4964. https://dx.doi.org/10.1109/TIP.2020.2975978 1057-7149 https://hdl.handle.net/10356/161038 10.1109/TIP.2020.2975978 32149636 2-s2.0-85082039115 29 4952 4964 en 2017-T1-002-110 2015-T2-2-114 IEEE Transactions on Image Processing © 2020 IEEE. All rights reserved. |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Engineering::Electrical and electronic engineering Training Image Color Analysis |
spellingShingle |
Engineering::Electrical and electronic engineering Training Image Color Analysis Ni, Zhangkai Ma, Kai-Kuang Zeng, Huanqiang Zhong, Baojiang Color image demosaicing using progressive collaborative representation |
description |
In this paper, a progressive collaborative representation (PCR) framework is proposed that is able to incorporate any existing color image demosaicing method for further boosting its demosaicing performance. Our PCR consists of two phases: (i) offline training and (ii) online refinement. In phase (i), multiple training-and-refining stages will be performed. In each stage, a new dictionary will be established through the learning of a large number of feature-patch pairs, extracted from the demosaicked images of the current stage and their corresponding original full-color images. After training, a projection matrix will be generated and exploited to refine the current demosaicked image. The updated image with improved image quality will be used as the input for the next training-and-refining stage and performed the same processing likewise. At the end of phase (i), all the projection matrices generated as above-mentioned will be exploited in phase (ii) to conduct online demosaicked image refinement of the test image. Extensive simulations conducted on two commonly-used test datasets (i.e., the IMAX and Kodak) for evaluating the demosaicing algorithms have clearly demonstrated that our proposed PCR framework is able to constantly boost the performance of any image demosaicing method we experimented, in terms of the objective and subjective performance evaluations. |
author2 |
School of Electrical and Electronic Engineering |
author_facet |
School of Electrical and Electronic Engineering Ni, Zhangkai Ma, Kai-Kuang Zeng, Huanqiang Zhong, Baojiang |
format |
Article |
author |
Ni, Zhangkai Ma, Kai-Kuang Zeng, Huanqiang Zhong, Baojiang |
author_sort |
Ni, Zhangkai |
title |
Color image demosaicing using progressive collaborative representation |
title_short |
Color image demosaicing using progressive collaborative representation |
title_full |
Color image demosaicing using progressive collaborative representation |
title_fullStr |
Color image demosaicing using progressive collaborative representation |
title_full_unstemmed |
Color image demosaicing using progressive collaborative representation |
title_sort |
color image demosaicing using progressive collaborative representation |
publishDate |
2022 |
url |
https://hdl.handle.net/10356/161038 |
_version_ |
1743119592633401344 |