Reducible Dictionaries for Single Image Super-Resolution based on Patch Matching and Mean Shifting

Pejman Rasti, Kamal Nasrollahi, Olga Orlova, Gert Tamberg, Thomas B. Moeslund, Gholamreza Anbarjafari

Research output: Contribution to journalJournal articleResearchpeer-review

7 Citations (Scopus)
127 Downloads (Pure)

Abstract

A single-image super-resolution (SR) method is proposed. The proposed method uses a generated dictionary from pairs of high resolution (HR) images and their corresponding low resolution (LR) representations. First, HR images and the corresponding LR ones are divided into patches of HR and LR, respectively, and then they are collected into separate dictionaries. Afterward, when performing SR, the distance between every patch of the input LR image and those of available LR patches in the LR dictionary is calculated. The minimum distance between the input LR patch and those in the LR dictionary is taken, and its counterpart from the HR dictionary is passed through an illumination enhancement process. By this technique, the noticeable change of illumination between neighbor patches in the super-resolved image is significantly reduced. The enhanced HR patch represents the HR patch of the super-resolved image. Finally, to remove the blocking effect caused by merging the patches, an average of the obtained HR image and the interpolated image obtained using bicubic interpolation is calculated. The quantitative and qualitative analyses show the superiority of the proposed technique over the conventional and state-of-art methods.
Original languageEnglish
JournalJournal of Electronic Imaging
Volume26
Issue number2
Number of pages9
ISSN1017-9909
DOIs
Publication statusPublished - 2017

Fingerprint

dictionaries
Glossaries
Image resolution
Optical resolving power
high resolution
Lighting
Merging
illumination
Interpolation
image resolution
interpolation
augmentation

Cite this

@article{c8f89831535a43c3b7933e0ea03a4941,
title = "Reducible Dictionaries for Single Image Super-Resolution based on Patch Matching and Mean Shifting",
abstract = "A single-image super-resolution (SR) method is proposed. The proposed method uses a generated dictionary from pairs of high resolution (HR) images and their corresponding low resolution (LR) representations. First, HR images and the corresponding LR ones are divided into patches of HR and LR, respectively, and then they are collected into separate dictionaries. Afterward, when performing SR, the distance between every patch of the input LR image and those of available LR patches in the LR dictionary is calculated. The minimum distance between the input LR patch and those in the LR dictionary is taken, and its counterpart from the HR dictionary is passed through an illumination enhancement process. By this technique, the noticeable change of illumination between neighbor patches in the super-resolved image is significantly reduced. The enhanced HR patch represents the HR patch of the super-resolved image. Finally, to remove the blocking effect caused by merging the patches, an average of the obtained HR image and the interpolated image obtained using bicubic interpolation is calculated. The quantitative and qualitative analyses show the superiority of the proposed technique over the conventional and state-of-art methods.",
author = "Pejman Rasti and Kamal Nasrollahi and Olga Orlova and Gert Tamberg and Moeslund, {Thomas B.} and Gholamreza Anbarjafari",
year = "2017",
doi = "10.1117/1.JEI.26.2.023024",
language = "English",
volume = "26",
journal = "Journal of Electronic Imaging",
issn = "1017-9909",
publisher = "Society of Photo-optical Instrumentation Engineers",
number = "2",

}

Reducible Dictionaries for Single Image Super-Resolution based on Patch Matching and Mean Shifting. / Rasti, Pejman; Nasrollahi, Kamal; Orlova, Olga; Tamberg, Gert; Moeslund, Thomas B.; Anbarjafari, Gholamreza.

In: Journal of Electronic Imaging, Vol. 26, No. 2, 2017.

Research output: Contribution to journalJournal articleResearchpeer-review

TY - JOUR

T1 - Reducible Dictionaries for Single Image Super-Resolution based on Patch Matching and Mean Shifting

AU - Rasti, Pejman

AU - Nasrollahi, Kamal

AU - Orlova, Olga

AU - Tamberg, Gert

AU - Moeslund, Thomas B.

AU - Anbarjafari, Gholamreza

PY - 2017

Y1 - 2017

N2 - A single-image super-resolution (SR) method is proposed. The proposed method uses a generated dictionary from pairs of high resolution (HR) images and their corresponding low resolution (LR) representations. First, HR images and the corresponding LR ones are divided into patches of HR and LR, respectively, and then they are collected into separate dictionaries. Afterward, when performing SR, the distance between every patch of the input LR image and those of available LR patches in the LR dictionary is calculated. The minimum distance between the input LR patch and those in the LR dictionary is taken, and its counterpart from the HR dictionary is passed through an illumination enhancement process. By this technique, the noticeable change of illumination between neighbor patches in the super-resolved image is significantly reduced. The enhanced HR patch represents the HR patch of the super-resolved image. Finally, to remove the blocking effect caused by merging the patches, an average of the obtained HR image and the interpolated image obtained using bicubic interpolation is calculated. The quantitative and qualitative analyses show the superiority of the proposed technique over the conventional and state-of-art methods.

AB - A single-image super-resolution (SR) method is proposed. The proposed method uses a generated dictionary from pairs of high resolution (HR) images and their corresponding low resolution (LR) representations. First, HR images and the corresponding LR ones are divided into patches of HR and LR, respectively, and then they are collected into separate dictionaries. Afterward, when performing SR, the distance between every patch of the input LR image and those of available LR patches in the LR dictionary is calculated. The minimum distance between the input LR patch and those in the LR dictionary is taken, and its counterpart from the HR dictionary is passed through an illumination enhancement process. By this technique, the noticeable change of illumination between neighbor patches in the super-resolved image is significantly reduced. The enhanced HR patch represents the HR patch of the super-resolved image. Finally, to remove the blocking effect caused by merging the patches, an average of the obtained HR image and the interpolated image obtained using bicubic interpolation is calculated. The quantitative and qualitative analyses show the superiority of the proposed technique over the conventional and state-of-art methods.

U2 - 10.1117/1.JEI.26.2.023024

DO - 10.1117/1.JEI.26.2.023024

M3 - Journal article

VL - 26

JO - Journal of Electronic Imaging

JF - Journal of Electronic Imaging

SN - 1017-9909

IS - 2

ER -