Framework for fair objective performance evaluation of single-image super-resolution algorithms

Won Hee Kim, Jong-Seok Lee

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Single-image super-resolution (SISR) is a technology to reconstruct a high-resolution image from a single low-resolution input image. The performance of SISR algorithms is usually evaluated by applying full-reference objective image quality assessment metrics. First, it is argued that the result of objective quality evaluation may become inconsistent with subjective quality assessment, depending on how the input low-resolution image is generated and how up-scaling during SISR is conducted. Since such inconsistency is due to subpixel-level misalignment between the original and output images, a framework is then proposed that compensates any spatial displacement between the two images and enables fair SISR performance evaluation using objective quality metrics.

Original languageEnglish
Pages (from-to)42-44
Number of pages3
JournalElectronics Letters
Volume51
Issue number1
DOIs
Publication statusPublished - 2015 Jan 1

Fingerprint

Image resolution
Optical resolving power
Image quality

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering

Cite this

@article{bb79c3219a5849778245a1c607fdb689,
title = "Framework for fair objective performance evaluation of single-image super-resolution algorithms",
abstract = "Single-image super-resolution (SISR) is a technology to reconstruct a high-resolution image from a single low-resolution input image. The performance of SISR algorithms is usually evaluated by applying full-reference objective image quality assessment metrics. First, it is argued that the result of objective quality evaluation may become inconsistent with subjective quality assessment, depending on how the input low-resolution image is generated and how up-scaling during SISR is conducted. Since such inconsistency is due to subpixel-level misalignment between the original and output images, a framework is then proposed that compensates any spatial displacement between the two images and enables fair SISR performance evaluation using objective quality metrics.",
author = "Kim, {Won Hee} and Jong-Seok Lee",
year = "2015",
month = "1",
day = "1",
doi = "10.1049/el.2014.2784",
language = "English",
volume = "51",
pages = "42--44",
journal = "Electronics Letters",
issn = "0013-5194",
publisher = "Institution of Engineering and Technology",
number = "1",

}

Framework for fair objective performance evaluation of single-image super-resolution algorithms. / Kim, Won Hee; Lee, Jong-Seok.

In: Electronics Letters, Vol. 51, No. 1, 01.01.2015, p. 42-44.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Framework for fair objective performance evaluation of single-image super-resolution algorithms

AU - Kim, Won Hee

AU - Lee, Jong-Seok

PY - 2015/1/1

Y1 - 2015/1/1

N2 - Single-image super-resolution (SISR) is a technology to reconstruct a high-resolution image from a single low-resolution input image. The performance of SISR algorithms is usually evaluated by applying full-reference objective image quality assessment metrics. First, it is argued that the result of objective quality evaluation may become inconsistent with subjective quality assessment, depending on how the input low-resolution image is generated and how up-scaling during SISR is conducted. Since such inconsistency is due to subpixel-level misalignment between the original and output images, a framework is then proposed that compensates any spatial displacement between the two images and enables fair SISR performance evaluation using objective quality metrics.

AB - Single-image super-resolution (SISR) is a technology to reconstruct a high-resolution image from a single low-resolution input image. The performance of SISR algorithms is usually evaluated by applying full-reference objective image quality assessment metrics. First, it is argued that the result of objective quality evaluation may become inconsistent with subjective quality assessment, depending on how the input low-resolution image is generated and how up-scaling during SISR is conducted. Since such inconsistency is due to subpixel-level misalignment between the original and output images, a framework is then proposed that compensates any spatial displacement between the two images and enables fair SISR performance evaluation using objective quality metrics.

UR - http://www.scopus.com/inward/record.url?scp=84919826163&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84919826163&partnerID=8YFLogxK

U2 - 10.1049/el.2014.2784

DO - 10.1049/el.2014.2784

M3 - Article

VL - 51

SP - 42

EP - 44

JO - Electronics Letters

JF - Electronics Letters

SN - 0013-5194

IS - 1

ER -