Analysis of Probability Density Functions in Existing No-Reference Image Quality Assessment Algorithm for Contrast-Distorted Images

Ismail Taha Ahmed, Chen Soong Der, Norziana Jamil, Baraa Tareq Hammad

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Amongst all distortion types, contrast change is very crucial for visual perception of image quality. Contrast distortion may be caused by poor lighting condition and poor quality image acquisition device. Contrast-distorted image (CDI) is defined as image with low dynamic range of brightness. Most of existing image quality assessment algorithms (IQAs) have been developed during the past decade. However, most of them are designed for images distorted by compression, noise and blurring. There are very few IQAs designed specifically for CDI, e.g. Reduced-reference Image Quality Metric for Contrast-changed images (RIQMC) and No Reference-Image Quality Assessment (NR-IQA) for Contrast-Distorted Images (NR-IQA-CDI). The five features used in NR-IQA-CDI are the global spatial statistics of an image including the mean, standard deviation, entropy, kurtosis and skewness. The statistical model or the Probability Density Function (PDF) for each of the given moment features were estimated using a public image database with large number of natural scene images. Because of poor performance in two out of three image databases, where the Pearson Correlation Coefficient (PLCC) were only 0.5739 and 0.7623 in TID2013 and CSIQ database, thus motivate us to further investigated to detect the gabs in existing NR-IQA-CDI. The paper can address the problem of existing NR-IQA-CDI which the bell-curve like probability density function (pdf) of the contrast related features like standard deviation and entropy does not correlate well with the monotonic relation between the contrast features and the perceived contrast level.

Original languageEnglish
Title of host publicationICSGRC 2019 - 2019 IEEE 10th Control and System Graduate Research Colloquium, Proceeding
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages133-137
Number of pages5
ISBN (Electronic)9781728107554
DOIs
Publication statusPublished - Aug 2019
Event10th IEEE Control and System Graduate Research Colloquium, ICSGRC 2019 - Shah Alam, Malaysia
Duration: 02 Aug 201903 Aug 2019

Publication series

NameICSGRC 2019 - 2019 IEEE 10th Control and System Graduate Research Colloquium, Proceeding

Conference

Conference10th IEEE Control and System Graduate Research Colloquium, ICSGRC 2019
CountryMalaysia
CityShah Alam
Period02/08/1903/08/19

Fingerprint

Image Quality Assessment
Probability density function
Image quality
Image Database
Entropy
Image Quality
Standard deviation
Bell curve
Image acquisition
Spatial Statistics
Pearson Correlation
Visual Perception
Luminance
Image Acquisition
Kurtosis
Skewness
Brightness
Dynamic Range
Lighting
Statistics

All Science Journal Classification (ASJC) codes

  • Process Chemistry and Technology
  • Electrical and Electronic Engineering
  • Control and Optimization
  • Artificial Intelligence
  • Computer Networks and Communications

Cite this

Ahmed, I. T., Der, C. S., Jamil, N., & Hammad, B. T. (2019). Analysis of Probability Density Functions in Existing No-Reference Image Quality Assessment Algorithm for Contrast-Distorted Images. In ICSGRC 2019 - 2019 IEEE 10th Control and System Graduate Research Colloquium, Proceeding (pp. 133-137). [8837095] (ICSGRC 2019 - 2019 IEEE 10th Control and System Graduate Research Colloquium, Proceeding). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICSGRC.2019.8837095
Ahmed, Ismail Taha ; Der, Chen Soong ; Jamil, Norziana ; Hammad, Baraa Tareq. / Analysis of Probability Density Functions in Existing No-Reference Image Quality Assessment Algorithm for Contrast-Distorted Images. ICSGRC 2019 - 2019 IEEE 10th Control and System Graduate Research Colloquium, Proceeding. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 133-137 (ICSGRC 2019 - 2019 IEEE 10th Control and System Graduate Research Colloquium, Proceeding).
@inproceedings{8a06c50443d54f35a28cf8accf3f57b7,
title = "Analysis of Probability Density Functions in Existing No-Reference Image Quality Assessment Algorithm for Contrast-Distorted Images",
abstract = "Amongst all distortion types, contrast change is very crucial for visual perception of image quality. Contrast distortion may be caused by poor lighting condition and poor quality image acquisition device. Contrast-distorted image (CDI) is defined as image with low dynamic range of brightness. Most of existing image quality assessment algorithms (IQAs) have been developed during the past decade. However, most of them are designed for images distorted by compression, noise and blurring. There are very few IQAs designed specifically for CDI, e.g. Reduced-reference Image Quality Metric for Contrast-changed images (RIQMC) and No Reference-Image Quality Assessment (NR-IQA) for Contrast-Distorted Images (NR-IQA-CDI). The five features used in NR-IQA-CDI are the global spatial statistics of an image including the mean, standard deviation, entropy, kurtosis and skewness. The statistical model or the Probability Density Function (PDF) for each of the given moment features were estimated using a public image database with large number of natural scene images. Because of poor performance in two out of three image databases, where the Pearson Correlation Coefficient (PLCC) were only 0.5739 and 0.7623 in TID2013 and CSIQ database, thus motivate us to further investigated to detect the gabs in existing NR-IQA-CDI. The paper can address the problem of existing NR-IQA-CDI which the bell-curve like probability density function (pdf) of the contrast related features like standard deviation and entropy does not correlate well with the monotonic relation between the contrast features and the perceived contrast level.",
author = "Ahmed, {Ismail Taha} and Der, {Chen Soong} and Norziana Jamil and Hammad, {Baraa Tareq}",
year = "2019",
month = "8",
doi = "10.1109/ICSGRC.2019.8837095",
language = "English",
series = "ICSGRC 2019 - 2019 IEEE 10th Control and System Graduate Research Colloquium, Proceeding",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "133--137",
booktitle = "ICSGRC 2019 - 2019 IEEE 10th Control and System Graduate Research Colloquium, Proceeding",
address = "United States",

}

Ahmed, IT, Der, CS, Jamil, N & Hammad, BT 2019, Analysis of Probability Density Functions in Existing No-Reference Image Quality Assessment Algorithm for Contrast-Distorted Images. in ICSGRC 2019 - 2019 IEEE 10th Control and System Graduate Research Colloquium, Proceeding., 8837095, ICSGRC 2019 - 2019 IEEE 10th Control and System Graduate Research Colloquium, Proceeding, Institute of Electrical and Electronics Engineers Inc., pp. 133-137, 10th IEEE Control and System Graduate Research Colloquium, ICSGRC 2019, Shah Alam, Malaysia, 02/08/19. https://doi.org/10.1109/ICSGRC.2019.8837095

Analysis of Probability Density Functions in Existing No-Reference Image Quality Assessment Algorithm for Contrast-Distorted Images. / Ahmed, Ismail Taha; Der, Chen Soong; Jamil, Norziana; Hammad, Baraa Tareq.

ICSGRC 2019 - 2019 IEEE 10th Control and System Graduate Research Colloquium, Proceeding. Institute of Electrical and Electronics Engineers Inc., 2019. p. 133-137 8837095 (ICSGRC 2019 - 2019 IEEE 10th Control and System Graduate Research Colloquium, Proceeding).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Analysis of Probability Density Functions in Existing No-Reference Image Quality Assessment Algorithm for Contrast-Distorted Images

AU - Ahmed, Ismail Taha

AU - Der, Chen Soong

AU - Jamil, Norziana

AU - Hammad, Baraa Tareq

PY - 2019/8

Y1 - 2019/8

N2 - Amongst all distortion types, contrast change is very crucial for visual perception of image quality. Contrast distortion may be caused by poor lighting condition and poor quality image acquisition device. Contrast-distorted image (CDI) is defined as image with low dynamic range of brightness. Most of existing image quality assessment algorithms (IQAs) have been developed during the past decade. However, most of them are designed for images distorted by compression, noise and blurring. There are very few IQAs designed specifically for CDI, e.g. Reduced-reference Image Quality Metric for Contrast-changed images (RIQMC) and No Reference-Image Quality Assessment (NR-IQA) for Contrast-Distorted Images (NR-IQA-CDI). The five features used in NR-IQA-CDI are the global spatial statistics of an image including the mean, standard deviation, entropy, kurtosis and skewness. The statistical model or the Probability Density Function (PDF) for each of the given moment features were estimated using a public image database with large number of natural scene images. Because of poor performance in two out of three image databases, where the Pearson Correlation Coefficient (PLCC) were only 0.5739 and 0.7623 in TID2013 and CSIQ database, thus motivate us to further investigated to detect the gabs in existing NR-IQA-CDI. The paper can address the problem of existing NR-IQA-CDI which the bell-curve like probability density function (pdf) of the contrast related features like standard deviation and entropy does not correlate well with the monotonic relation between the contrast features and the perceived contrast level.

AB - Amongst all distortion types, contrast change is very crucial for visual perception of image quality. Contrast distortion may be caused by poor lighting condition and poor quality image acquisition device. Contrast-distorted image (CDI) is defined as image with low dynamic range of brightness. Most of existing image quality assessment algorithms (IQAs) have been developed during the past decade. However, most of them are designed for images distorted by compression, noise and blurring. There are very few IQAs designed specifically for CDI, e.g. Reduced-reference Image Quality Metric for Contrast-changed images (RIQMC) and No Reference-Image Quality Assessment (NR-IQA) for Contrast-Distorted Images (NR-IQA-CDI). The five features used in NR-IQA-CDI are the global spatial statistics of an image including the mean, standard deviation, entropy, kurtosis and skewness. The statistical model or the Probability Density Function (PDF) for each of the given moment features were estimated using a public image database with large number of natural scene images. Because of poor performance in two out of three image databases, where the Pearson Correlation Coefficient (PLCC) were only 0.5739 and 0.7623 in TID2013 and CSIQ database, thus motivate us to further investigated to detect the gabs in existing NR-IQA-CDI. The paper can address the problem of existing NR-IQA-CDI which the bell-curve like probability density function (pdf) of the contrast related features like standard deviation and entropy does not correlate well with the monotonic relation between the contrast features and the perceived contrast level.

UR - http://www.scopus.com/inward/record.url?scp=85073247540&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85073247540&partnerID=8YFLogxK

U2 - 10.1109/ICSGRC.2019.8837095

DO - 10.1109/ICSGRC.2019.8837095

M3 - Conference contribution

AN - SCOPUS:85073247540

T3 - ICSGRC 2019 - 2019 IEEE 10th Control and System Graduate Research Colloquium, Proceeding

SP - 133

EP - 137

BT - ICSGRC 2019 - 2019 IEEE 10th Control and System Graduate Research Colloquium, Proceeding

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Ahmed IT, Der CS, Jamil N, Hammad BT. Analysis of Probability Density Functions in Existing No-Reference Image Quality Assessment Algorithm for Contrast-Distorted Images. In ICSGRC 2019 - 2019 IEEE 10th Control and System Graduate Research Colloquium, Proceeding. Institute of Electrical and Electronics Engineers Inc. 2019. p. 133-137. 8837095. (ICSGRC 2019 - 2019 IEEE 10th Control and System Graduate Research Colloquium, Proceeding). https://doi.org/10.1109/ICSGRC.2019.8837095