A new low-complexity patch-based image super-resolution

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

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

7 Citationer (Scopus)

Resumé

In this paper, a novel single image super-resolution method, which uses a generated dic- tionary from pairs of high resolution (HR) images and their corresponding low resolution (LR) representations, is proposed. First, HR and LR dictionaries are created by dividing HR and LR images into patches Afterwards, when performing SR, the distance between every patch of the input LR image and those of available LR patches in the LR dictionary are calculated. The minimum distance between the input LR patch and those in the LR dictionary is taken, and its counterpart from the HR dictionary will be passed through an illumination enhancement process resulting in consistency of illumination between neigh- bour patches. This process is applied to all patches of the LR image. Finally, in order to remove the blocking effect caused by merging the patches, an average of the obtained HR image and the interpolated image is calculated. Furthermore, it is shown that the size of dictionaries is reducible to a great degree. The speed of the system is improved by 62.5%. The quantitative and qualitative analyses of the experimental results show the superiority of the proposed technique over the conventional and state-of-the-art methods.
OriginalsprogEngelsk
TidsskriftIET Computer Vision
Vol/bind11
Udgave nummer7
Sider (fra-til)567-576
Antal sider10
ISSN1751-9632
DOI
StatusUdgivet - 2017

Fingerprint

Glossaries
Image resolution
Optical resolving power
Lighting
Merging

Citer dette

Rasti, Pejman ; Nasrollahi, Kamal ; Orlova, Olga ; Tamberg, Gert ; Ozcinar, Cagri ; Moeslund, Thomas B. ; Anbarjafari, Gholamreza. / A new low-complexity patch-based image super-resolution. I: IET Computer Vision. 2017 ; Bind 11, Nr. 7. s. 567-576.
@article{089871a2e2bc4966bd39a5cf21cdf331,
title = "A new low-complexity patch-based image super-resolution",
abstract = "In this paper, a novel single image super-resolution method, which uses a generated dic- tionary from pairs of high resolution (HR) images and their corresponding low resolution (LR) representations, is proposed. First, HR and LR dictionaries are created by dividing HR and LR images into patches Afterwards, when performing SR, the distance between every patch of the input LR image and those of available LR patches in the LR dictionary are calculated. The minimum distance between the input LR patch and those in the LR dictionary is taken, and its counterpart from the HR dictionary will be passed through an illumination enhancement process resulting in consistency of illumination between neigh- bour patches. This process is applied to all patches of the LR image. Finally, in order to remove the blocking effect caused by merging the patches, an average of the obtained HR image and the interpolated image is calculated. Furthermore, it is shown that the size of dictionaries is reducible to a great degree. The speed of the system is improved by 62.5{\%}. The quantitative and qualitative analyses of the experimental results show the superiority of the proposed technique over the conventional and state-of-the-art methods.",
keywords = "Super-Resolution, Dictionary Reduction, Patch Processing, Resolution Enhancement",
author = "Pejman Rasti and Kamal Nasrollahi and Olga Orlova and Gert Tamberg and Cagri Ozcinar and Moeslund, {Thomas B.} and Gholamreza Anbarjafari",
year = "2017",
doi = "10.1049/iet-cvi.2016.0463",
language = "English",
volume = "11",
pages = "567--576",
journal = "IET Computer Vision",
issn = "1751-9632",
publisher = "Institution of Engineering and Technology",
number = "7",

}

Rasti, P, Nasrollahi, K, Orlova, O, Tamberg, G, Ozcinar, C, Moeslund, TB & Anbarjafari, G 2017, 'A new low-complexity patch-based image super-resolution', IET Computer Vision, bind 11, nr. 7, s. 567-576. https://doi.org/10.1049/iet-cvi.2016.0463

A new low-complexity patch-based image super-resolution. / Rasti, Pejman; Nasrollahi, Kamal; Orlova, Olga; Tamberg, Gert; Ozcinar, Cagri; Moeslund, Thomas B.; Anbarjafari, Gholamreza.

I: IET Computer Vision, Bind 11, Nr. 7, 2017, s. 567-576.

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

TY - JOUR

T1 - A new low-complexity patch-based image super-resolution

AU - Rasti, Pejman

AU - Nasrollahi, Kamal

AU - Orlova, Olga

AU - Tamberg, Gert

AU - Ozcinar, Cagri

AU - Moeslund, Thomas B.

AU - Anbarjafari, Gholamreza

PY - 2017

Y1 - 2017

N2 - In this paper, a novel single image super-resolution method, which uses a generated dic- tionary from pairs of high resolution (HR) images and their corresponding low resolution (LR) representations, is proposed. First, HR and LR dictionaries are created by dividing HR and LR images into patches Afterwards, when performing SR, the distance between every patch of the input LR image and those of available LR patches in the LR dictionary are calculated. The minimum distance between the input LR patch and those in the LR dictionary is taken, and its counterpart from the HR dictionary will be passed through an illumination enhancement process resulting in consistency of illumination between neigh- bour patches. This process is applied to all patches of the LR image. Finally, in order to remove the blocking effect caused by merging the patches, an average of the obtained HR image and the interpolated image is calculated. Furthermore, it is shown that the size of dictionaries is reducible to a great degree. The speed of the system is improved by 62.5%. The quantitative and qualitative analyses of the experimental results show the superiority of the proposed technique over the conventional and state-of-the-art methods.

AB - In this paper, a novel single image super-resolution method, which uses a generated dic- tionary from pairs of high resolution (HR) images and their corresponding low resolution (LR) representations, is proposed. First, HR and LR dictionaries are created by dividing HR and LR images into patches Afterwards, when performing SR, the distance between every patch of the input LR image and those of available LR patches in the LR dictionary are calculated. The minimum distance between the input LR patch and those in the LR dictionary is taken, and its counterpart from the HR dictionary will be passed through an illumination enhancement process resulting in consistency of illumination between neigh- bour patches. This process is applied to all patches of the LR image. Finally, in order to remove the blocking effect caused by merging the patches, an average of the obtained HR image and the interpolated image is calculated. Furthermore, it is shown that the size of dictionaries is reducible to a great degree. The speed of the system is improved by 62.5%. The quantitative and qualitative analyses of the experimental results show the superiority of the proposed technique over the conventional and state-of-the-art methods.

KW - Super-Resolution

KW - Dictionary Reduction

KW - Patch Processing

KW - Resolution Enhancement

U2 - 10.1049/iet-cvi.2016.0463

DO - 10.1049/iet-cvi.2016.0463

M3 - Journal article

VL - 11

SP - 567

EP - 576

JO - IET Computer Vision

JF - IET Computer Vision

SN - 1751-9632

IS - 7

ER -