Analysis and improvement on statistical naturalness measure

Although Statistical Naturalness Measure (SNM) can rate the naturalness of image�s contrast relatively well, but it suffers from the problem of inconsistent rating across different spatial resolution; ratings for images with identical content and contrast level but different spatial resolution might...

Full description

Saved in:
Bibliographic Details
Main Authors: Ismail N.H.B., Chen S.-D.
Other Authors: 57089831500
Format: Article
Published: Asian Research Publishing Network 2023
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.uniten.dspace-22858
record_format dspace
spelling my.uniten.dspace-228582023-05-29T14:12:47Z Analysis and improvement on statistical naturalness measure Ismail N.H.B. Chen S.-D. 57089831500 7410253413 Although Statistical Naturalness Measure (SNM) can rate the naturalness of image�s contrast relatively well, but it suffers from the problem of inconsistent rating across different spatial resolution; ratings for images with identical content and contrast level but different spatial resolution might be significantly different. The statistical model SNM was developed upon sample images with certain spatial resolution and the contrast was defined using a specific block size. This paper suggests that the problem is due to the computation of contrast using fixed block size regardless of the spatial resolution of the input image. It is proposed to rescale the block size based on the spatial resolution of input image to keep the ratio of block size to image size similar to those of the sample images used in developing the statistical model of SNM. The proposed method is tested and proven statistically to be effective in reducing the inconsistency in the ratings of images across different spatial resolution such there is no significant difference among them. � 2005 - 2016 JATIT & LLS. All rights reserved. Final 2023-05-29T06:12:47Z 2023-05-29T06:12:47Z 2016 Article 2-s2.0-84956691380 https://www.scopus.com/inward/record.uri?eid=2-s2.0-84956691380&partnerID=40&md5=dd7a0bcb8f2e24cf2b140ffc4b16c5e0 https://irepository.uniten.edu.my/handle/123456789/22858 83 3 368 372 Asian Research Publishing Network Scopus
institution Universiti Tenaga Nasional
building UNITEN Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Tenaga Nasional
content_source UNITEN Institutional Repository
url_provider http://dspace.uniten.edu.my/
description Although Statistical Naturalness Measure (SNM) can rate the naturalness of image�s contrast relatively well, but it suffers from the problem of inconsistent rating across different spatial resolution; ratings for images with identical content and contrast level but different spatial resolution might be significantly different. The statistical model SNM was developed upon sample images with certain spatial resolution and the contrast was defined using a specific block size. This paper suggests that the problem is due to the computation of contrast using fixed block size regardless of the spatial resolution of the input image. It is proposed to rescale the block size based on the spatial resolution of input image to keep the ratio of block size to image size similar to those of the sample images used in developing the statistical model of SNM. The proposed method is tested and proven statistically to be effective in reducing the inconsistency in the ratings of images across different spatial resolution such there is no significant difference among them. � 2005 - 2016 JATIT & LLS. All rights reserved.
author2 57089831500
author_facet 57089831500
Ismail N.H.B.
Chen S.-D.
format Article
author Ismail N.H.B.
Chen S.-D.
spellingShingle Ismail N.H.B.
Chen S.-D.
Analysis and improvement on statistical naturalness measure
author_sort Ismail N.H.B.
title Analysis and improvement on statistical naturalness measure
title_short Analysis and improvement on statistical naturalness measure
title_full Analysis and improvement on statistical naturalness measure
title_fullStr Analysis and improvement on statistical naturalness measure
title_full_unstemmed Analysis and improvement on statistical naturalness measure
title_sort analysis and improvement on statistical naturalness measure
publisher Asian Research Publishing Network
publishDate 2023
_version_ 1806423268037492736
score 13.214268