Enhancement of no-reference image quality assessment for contrast-distorted images using natural scene statistics features in Curvelet domain

Ismail Taha Ahmed, Soong Der Chen

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

Abstract

Contrast is a very important characteristic for visual perception of image quality. Some No-Reference Image Quality Assessment Algorithm NR-IQA metrics for Contrast-Distorted Images (CDI) have been proposed in the literature, e.g. Reduced-reference Image Quality Metric for Contrast-changed images (RIQMC) and NR-IQA for Contrast-Distorted Images (NR-IQACDI). Here, we intend to improve the assessment results of images available in databases such as TID2013 and CSIQ. Most of the NR-IQA metrics (e.g. NR-IQACDI) designed for CDI adopt features available in the spatial domain. This paper proposes to compliment it with feature in Curvelet domain which is powerful in capturing multiscale and multidirectional information in an image. We employed the Natural Scene Statistics (NSS) features in Curvelet domain originally recommended by Liu et al. (2014) which were found useful in the assessment of the quality of image distorted by compression, noise and blurring. Experiments were then conducted to assess the effect of incorporating these NSS features. The experimental results based on K-fold cross validation (K ranged from 2 to 10) and statistical test showed that the performance of NRIQACDI was improved. Future works include improvements of NRIQACDI, exploration of feature fusion methods and using a suitable feature selection method.

Original languageEnglish
Title of host publication2017 7th IEEE International Conference on System Engineering and Technology, ICSET 2017 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages128-133
Number of pages6
ISBN (Electronic)9781538603833
DOIs
Publication statusPublished - 27 Nov 2017
Event7th IEEE International Conference on System Engineering and Technology, ICSET 2017 - Shah Alam, Malaysia
Duration: 02 Oct 201703 Oct 2017

Other

Other7th IEEE International Conference on System Engineering and Technology, ICSET 2017
CountryMalaysia
CityShah Alam
Period02/10/1703/10/17

Fingerprint

Curvelet
Image Quality Assessment
Image quality
Enhancement
Statistics
Statistical tests
Feature extraction
Fusion reactions
Metric
Image Quality
Visual Perception
Statistical test
Experiments
Cross-validation
Feature Selection
Fusion
Fold
Compression

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Control and Optimization
  • Computer Networks and Communications
  • Human-Computer Interaction

Cite this

Ahmed, I. T., & Chen, S. D. (2017). Enhancement of no-reference image quality assessment for contrast-distorted images using natural scene statistics features in Curvelet domain. In 2017 7th IEEE International Conference on System Engineering and Technology, ICSET 2017 - Proceedings (pp. 128-133). [8123433] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICSEngT.2017.8123433
Ahmed, Ismail Taha ; Chen, Soong Der. / Enhancement of no-reference image quality assessment for contrast-distorted images using natural scene statistics features in Curvelet domain. 2017 7th IEEE International Conference on System Engineering and Technology, ICSET 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 128-133
@inproceedings{f2c67bf049764ac5a41f81e812ea8eeb,
title = "Enhancement of no-reference image quality assessment for contrast-distorted images using natural scene statistics features in Curvelet domain",
abstract = "Contrast is a very important characteristic for visual perception of image quality. Some No-Reference Image Quality Assessment Algorithm NR-IQA metrics for Contrast-Distorted Images (CDI) have been proposed in the literature, e.g. Reduced-reference Image Quality Metric for Contrast-changed images (RIQMC) and NR-IQA for Contrast-Distorted Images (NR-IQACDI). Here, we intend to improve the assessment results of images available in databases such as TID2013 and CSIQ. Most of the NR-IQA metrics (e.g. NR-IQACDI) designed for CDI adopt features available in the spatial domain. This paper proposes to compliment it with feature in Curvelet domain which is powerful in capturing multiscale and multidirectional information in an image. We employed the Natural Scene Statistics (NSS) features in Curvelet domain originally recommended by Liu et al. (2014) which were found useful in the assessment of the quality of image distorted by compression, noise and blurring. Experiments were then conducted to assess the effect of incorporating these NSS features. The experimental results based on K-fold cross validation (K ranged from 2 to 10) and statistical test showed that the performance of NRIQACDI was improved. Future works include improvements of NRIQACDI, exploration of feature fusion methods and using a suitable feature selection method.",
author = "Ahmed, {Ismail Taha} and Chen, {Soong Der}",
year = "2017",
month = "11",
day = "27",
doi = "10.1109/ICSEngT.2017.8123433",
language = "English",
pages = "128--133",
booktitle = "2017 7th IEEE International Conference on System Engineering and Technology, ICSET 2017 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

Ahmed, IT & Chen, SD 2017, Enhancement of no-reference image quality assessment for contrast-distorted images using natural scene statistics features in Curvelet domain. in 2017 7th IEEE International Conference on System Engineering and Technology, ICSET 2017 - Proceedings., 8123433, Institute of Electrical and Electronics Engineers Inc., pp. 128-133, 7th IEEE International Conference on System Engineering and Technology, ICSET 2017, Shah Alam, Malaysia, 02/10/17. https://doi.org/10.1109/ICSEngT.2017.8123433

Enhancement of no-reference image quality assessment for contrast-distorted images using natural scene statistics features in Curvelet domain. / Ahmed, Ismail Taha; Chen, Soong Der.

2017 7th IEEE International Conference on System Engineering and Technology, ICSET 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. p. 128-133 8123433.

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

TY - GEN

T1 - Enhancement of no-reference image quality assessment for contrast-distorted images using natural scene statistics features in Curvelet domain

AU - Ahmed, Ismail Taha

AU - Chen, Soong Der

PY - 2017/11/27

Y1 - 2017/11/27

N2 - Contrast is a very important characteristic for visual perception of image quality. Some No-Reference Image Quality Assessment Algorithm NR-IQA metrics for Contrast-Distorted Images (CDI) have been proposed in the literature, e.g. Reduced-reference Image Quality Metric for Contrast-changed images (RIQMC) and NR-IQA for Contrast-Distorted Images (NR-IQACDI). Here, we intend to improve the assessment results of images available in databases such as TID2013 and CSIQ. Most of the NR-IQA metrics (e.g. NR-IQACDI) designed for CDI adopt features available in the spatial domain. This paper proposes to compliment it with feature in Curvelet domain which is powerful in capturing multiscale and multidirectional information in an image. We employed the Natural Scene Statistics (NSS) features in Curvelet domain originally recommended by Liu et al. (2014) which were found useful in the assessment of the quality of image distorted by compression, noise and blurring. Experiments were then conducted to assess the effect of incorporating these NSS features. The experimental results based on K-fold cross validation (K ranged from 2 to 10) and statistical test showed that the performance of NRIQACDI was improved. Future works include improvements of NRIQACDI, exploration of feature fusion methods and using a suitable feature selection method.

AB - Contrast is a very important characteristic for visual perception of image quality. Some No-Reference Image Quality Assessment Algorithm NR-IQA metrics for Contrast-Distorted Images (CDI) have been proposed in the literature, e.g. Reduced-reference Image Quality Metric for Contrast-changed images (RIQMC) and NR-IQA for Contrast-Distorted Images (NR-IQACDI). Here, we intend to improve the assessment results of images available in databases such as TID2013 and CSIQ. Most of the NR-IQA metrics (e.g. NR-IQACDI) designed for CDI adopt features available in the spatial domain. This paper proposes to compliment it with feature in Curvelet domain which is powerful in capturing multiscale and multidirectional information in an image. We employed the Natural Scene Statistics (NSS) features in Curvelet domain originally recommended by Liu et al. (2014) which were found useful in the assessment of the quality of image distorted by compression, noise and blurring. Experiments were then conducted to assess the effect of incorporating these NSS features. The experimental results based on K-fold cross validation (K ranged from 2 to 10) and statistical test showed that the performance of NRIQACDI was improved. Future works include improvements of NRIQACDI, exploration of feature fusion methods and using a suitable feature selection method.

UR - http://www.scopus.com/inward/record.url?scp=85041393336&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85041393336&partnerID=8YFLogxK

U2 - 10.1109/ICSEngT.2017.8123433

DO - 10.1109/ICSEngT.2017.8123433

M3 - Conference contribution

SP - 128

EP - 133

BT - 2017 7th IEEE International Conference on System Engineering and Technology, ICSET 2017 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Ahmed IT, Chen SD. Enhancement of no-reference image quality assessment for contrast-distorted images using natural scene statistics features in Curvelet domain. In 2017 7th IEEE International Conference on System Engineering and Technology, ICSET 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2017. p. 128-133. 8123433 https://doi.org/10.1109/ICSEngT.2017.8123433