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

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...

Full description

Saved in:
Bibliographic Details
Published inElectronics letters Vol. 51; no. 1; pp. 42 - 44
Main Authors Kim, Won-Hee, Lee, Jong-Seok
Format Journal Article
LanguageEnglish
Published The Institution of Engineering and Technology 08.01.2015
Subjects
Algorithms
Assessments
Displacement
fair objective performance evaluation
full‐reference objective image quality assessment metrics
high‐resolution image reconstruction
Image and vision processing and display technology
Image quality
Image reconstruction
image resolution
input low‐resolution image generation
IQA metrics
Misalignment
objective quality evaluation
Performance evaluation
Quality assessment
single‐image super‐resolution algorithms
SISR algorithms
spatial displacement
subpixel‐level misalignment
fair objective performance evaluation
single-image super-resolution algorithms
objective quality evaluation
high-resolution image reconstruction
full-reference objective image quality assessment metrics
spatial displacement
image reconstruction
input low-resolution image generation
image resolution
IQA metrics
SISR algorithms
subpixel-level misalignment
Online AccessGet full text

Cover

More Information
Summary: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.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0013-5194
1350-911X
1350-911X
DOI:10.1049/el.2014.2784