An analysis of image quality assessment algorithm to detect the presence of unnatural contrast enhancement

Nur Halilah Binti Ismail, Soong Der Chen, Liang Shing Ng, Abd Rahman Ramli

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Image contrast enhancement purposely aim the visibility of image to be increased. Most of these problems may happen after contrast enhancement: amplification of noise artifacts, saturation-loss of details, excessive brightness change and unnatural contrast enhancement. The main objective of this paper is to present an extensive review on existing Image Quality Assessment Algorithm (IQA) in order to detect the presence of unnatural contrast enhancement. Basically, the IQA used produced quality rating of the image while consistently with human visual perception. Current IQA to detect presence of unnatural contrast enhancement: Lightness Order Error (LOE), Structure Measure Operator (SMO) and Statistical Naturalness Measure (SNM). However, result of current IQA evaluation shows it may not giving consistent quality rating with human visual perception. Among three IQAs, SNM demonstrate better performance compared to LOE and SMO. But, it suffers with consistent rating for different spatial image resolution in same image content. Thus, an improvement suggested in this paper to overcome such problem occurred.

Original languageEnglish
Pages (from-to)415-422
Number of pages8
JournalJournal of Theoretical and Applied Information Technology
Volume83
Issue number3
Publication statusPublished - 31 Jan 2016

Fingerprint

Image Quality Assessment
Contrast Enhancement
Image quality
Visual Perception
Human Perception
Image resolution
Visibility
Image Enhancement
Amplification
Luminance
Brightness
Operator
Saturation
Evaluation
Demonstrate

All Science Journal Classification (ASJC) codes

  • Theoretical Computer Science
  • Computer Science(all)

Cite this

@article{4da574ac9caa486da279f142d7b9831b,
title = "An analysis of image quality assessment algorithm to detect the presence of unnatural contrast enhancement",
abstract = "Image contrast enhancement purposely aim the visibility of image to be increased. Most of these problems may happen after contrast enhancement: amplification of noise artifacts, saturation-loss of details, excessive brightness change and unnatural contrast enhancement. The main objective of this paper is to present an extensive review on existing Image Quality Assessment Algorithm (IQA) in order to detect the presence of unnatural contrast enhancement. Basically, the IQA used produced quality rating of the image while consistently with human visual perception. Current IQA to detect presence of unnatural contrast enhancement: Lightness Order Error (LOE), Structure Measure Operator (SMO) and Statistical Naturalness Measure (SNM). However, result of current IQA evaluation shows it may not giving consistent quality rating with human visual perception. Among three IQAs, SNM demonstrate better performance compared to LOE and SMO. But, it suffers with consistent rating for different spatial image resolution in same image content. Thus, an improvement suggested in this paper to overcome such problem occurred.",
author = "Ismail, {Nur Halilah Binti} and Chen, {Soong Der} and Ng, {Liang Shing} and Ramli, {Abd Rahman}",
year = "2016",
month = "1",
day = "31",
language = "English",
volume = "83",
pages = "415--422",
journal = "Journal of Theoretical and Applied Information Technology",
issn = "1992-8645",
publisher = "Asian Research Publishing Network (ARPN)",
number = "3",

}

An analysis of image quality assessment algorithm to detect the presence of unnatural contrast enhancement. / Ismail, Nur Halilah Binti; Chen, Soong Der; Ng, Liang Shing; Ramli, Abd Rahman.

In: Journal of Theoretical and Applied Information Technology, Vol. 83, No. 3, 31.01.2016, p. 415-422.

Research output: Contribution to journalArticle

TY - JOUR

T1 - An analysis of image quality assessment algorithm to detect the presence of unnatural contrast enhancement

AU - Ismail, Nur Halilah Binti

AU - Chen, Soong Der

AU - Ng, Liang Shing

AU - Ramli, Abd Rahman

PY - 2016/1/31

Y1 - 2016/1/31

N2 - Image contrast enhancement purposely aim the visibility of image to be increased. Most of these problems may happen after contrast enhancement: amplification of noise artifacts, saturation-loss of details, excessive brightness change and unnatural contrast enhancement. The main objective of this paper is to present an extensive review on existing Image Quality Assessment Algorithm (IQA) in order to detect the presence of unnatural contrast enhancement. Basically, the IQA used produced quality rating of the image while consistently with human visual perception. Current IQA to detect presence of unnatural contrast enhancement: Lightness Order Error (LOE), Structure Measure Operator (SMO) and Statistical Naturalness Measure (SNM). However, result of current IQA evaluation shows it may not giving consistent quality rating with human visual perception. Among three IQAs, SNM demonstrate better performance compared to LOE and SMO. But, it suffers with consistent rating for different spatial image resolution in same image content. Thus, an improvement suggested in this paper to overcome such problem occurred.

AB - Image contrast enhancement purposely aim the visibility of image to be increased. Most of these problems may happen after contrast enhancement: amplification of noise artifacts, saturation-loss of details, excessive brightness change and unnatural contrast enhancement. The main objective of this paper is to present an extensive review on existing Image Quality Assessment Algorithm (IQA) in order to detect the presence of unnatural contrast enhancement. Basically, the IQA used produced quality rating of the image while consistently with human visual perception. Current IQA to detect presence of unnatural contrast enhancement: Lightness Order Error (LOE), Structure Measure Operator (SMO) and Statistical Naturalness Measure (SNM). However, result of current IQA evaluation shows it may not giving consistent quality rating with human visual perception. Among three IQAs, SNM demonstrate better performance compared to LOE and SMO. But, it suffers with consistent rating for different spatial image resolution in same image content. Thus, an improvement suggested in this paper to overcome such problem occurred.

UR - http://www.scopus.com/inward/record.url?scp=84956706871&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84956706871&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:84956706871

VL - 83

SP - 415

EP - 422

JO - Journal of Theoretical and Applied Information Technology

JF - Journal of Theoretical and Applied Information Technology

SN - 1992-8645

IS - 3

ER -