Staff View: A new image quality measure for assessment of histogram equalization-based contrast enhancement techniques

A new image quality measure for assessment of histogram equalization-based contrast enhancement techniques

Absolute Mean Brightness Error (AMBE) and Entropy are among the two most popular IQMs used to assess Histogram Equalization (HE) based techniques. To the best of author's knowledge, there is no evaluation report on how well the two IQMs correlate to human opinion. This paper reviews and discuss...

Full description

Saved in:

Bibliographic Details
Main Author:	Chen S.-D.
Other Authors:	7410253413
Format:	Article
Published:	Elsevier Inc. 2023
Subjects:	Contrast enhancement Distortions Histogram equalization Quality measures Visual perception Correlation methods Distortion (waves) Entropy Equalizers Graphic methods Image enhancement Mean square error Quality control Vision Contrast Enhancement Histogram equalizations Information fidelity criterion Pearson correlation coefficients Root mean square errors Subjective quality assessments Image quality
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my.uniten.dspace-30365
record_format	dspace
spelling	my.uniten.dspace-303652023-12-29T15:47:05Z A new image quality measure for assessment of histogram equalization-based contrast enhancement techniques Chen S.-D. 7410253413 Contrast enhancement Distortions Histogram equalization Quality measures Visual perception Correlation methods Distortion (waves) Entropy Equalizers Graphic methods Image enhancement Mean square error Quality control Vision Contrast Enhancement Histogram equalizations Information fidelity criterion Pearson correlation coefficients Quality measures Root mean square errors Subjective quality assessments Visual perception Image quality Absolute Mean Brightness Error (AMBE) and Entropy are among the two most popular IQMs used to assess Histogram Equalization (HE) based techniques. To the best of author's knowledge, there is no evaluation report on how well the two IQMs correlate to human opinion. This paper reviews and discusses the potential flaws in using AMBE and Entropy to assess HE-based techniques. This paper presents results of a subjective quality assessment in which image quality data obtained from 1935 human observer opinion scores were used to evaluate the IQMs. The statistical evaluation results show that the two IQMs have poor correlation with human mean opinion score (MOS); Pearson Correlation Coefficient (PCC)<0.4, Root Mean Square Error (RMSE)>0.75, Outlier Ratio (OR)>20%. A new IQM which takes into account important properties of human visual perception (HVP) is proposed. It is tested and found to have significantly better correlation (PCC>0.86, RMSE<0.39 and OR=0%). The proposed IQM also outperforms Multi-Scale Structural Similarity (MSSIM) and Information Fidelity Criterion-based (IFC) measure, which are two prominent fidelity-based IQMs. � 2012 Elsevier Inc. All rights reserved. Final 2023-12-29T07:47:05Z 2023-12-29T07:47:05Z 2012 Article 10.1016/j.dsp.2012.04.002 2-s2.0-84860669159 https://www.scopus.com/inward/record.uri?eid=2-s2.0-84860669159&doi=10.1016%2fj.dsp.2012.04.002&partnerID=40&md5=9e31b80877be3f5f6f83bf661b961bb7 https://irepository.uniten.edu.my/handle/123456789/30365 22 4 640 647 Elsevier Inc. 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/
topic	Contrast enhancement Distortions Histogram equalization Quality measures Visual perception Correlation methods Distortion (waves) Entropy Equalizers Graphic methods Image enhancement Mean square error Quality control Vision Contrast Enhancement Histogram equalizations Information fidelity criterion Pearson correlation coefficients Quality measures Root mean square errors Subjective quality assessments Visual perception Image quality
spellingShingle	Contrast enhancement Distortions Histogram equalization Quality measures Visual perception Correlation methods Distortion (waves) Entropy Equalizers Graphic methods Image enhancement Mean square error Quality control Vision Contrast Enhancement Histogram equalizations Information fidelity criterion Pearson correlation coefficients Quality measures Root mean square errors Subjective quality assessments Visual perception Image quality Chen S.-D. A new image quality measure for assessment of histogram equalization-based contrast enhancement techniques
description	Absolute Mean Brightness Error (AMBE) and Entropy are among the two most popular IQMs used to assess Histogram Equalization (HE) based techniques. To the best of author's knowledge, there is no evaluation report on how well the two IQMs correlate to human opinion. This paper reviews and discusses the potential flaws in using AMBE and Entropy to assess HE-based techniques. This paper presents results of a subjective quality assessment in which image quality data obtained from 1935 human observer opinion scores were used to evaluate the IQMs. The statistical evaluation results show that the two IQMs have poor correlation with human mean opinion score (MOS); Pearson Correlation Coefficient (PCC)<0.4, Root Mean Square Error (RMSE)>0.75, Outlier Ratio (OR)>20%. A new IQM which takes into account important properties of human visual perception (HVP) is proposed. It is tested and found to have significantly better correlation (PCC>0.86, RMSE<0.39 and OR=0%). The proposed IQM also outperforms Multi-Scale Structural Similarity (MSSIM) and Information Fidelity Criterion-based (IFC) measure, which are two prominent fidelity-based IQMs. � 2012 Elsevier Inc. All rights reserved.
author2	7410253413
author_facet	7410253413 Chen S.-D.
format	Article
author	Chen S.-D.
author_sort	Chen S.-D.
title	A new image quality measure for assessment of histogram equalization-based contrast enhancement techniques
title_short	A new image quality measure for assessment of histogram equalization-based contrast enhancement techniques
title_full	A new image quality measure for assessment of histogram equalization-based contrast enhancement techniques
title_fullStr	A new image quality measure for assessment of histogram equalization-based contrast enhancement techniques
title_full_unstemmed	A new image quality measure for assessment of histogram equalization-based contrast enhancement techniques
title_sort	new image quality measure for assessment of histogram equalization-based contrast enhancement techniques
publisher	Elsevier Inc.
publishDate	2023
_version_	1806427304632516608
score	13.211869

A new image quality measure for assessment of histogram equalization-based contrast enhancement techniques

Similar Items