Image Quality Assessment Based on Multi-Order Local Features Description, Modeling and Quantification

Yong DING; Xinyu ZHAO; Zhi ZHANG; Hang DAI

doi:10.1587/transinf.2016EDP7244

Image Quality Assessment Based on Multi-Order Local Features Description, Modeling and Quantification

Yong DING, Xinyu ZHAO, Zhi ZHANG, Hang DAI

Full Text Views

0

Share
Cite this

Summary :

Image quality assessment (IQA) plays an important role in quality monitoring, evaluation and optimization for image processing systems. However, current quality-aware feature extraction methods for IQA can hardly balance accuracy and complexity. This paper introduces multi-order local description into image quality assessment for feature extraction. The first-order structure derivative and high-order discriminative information are integrated into local pattern representation to serve as the quality-aware features. Then joint distributions of the local pattern representation are modeled by spatially enhanced histogram. Finally, the image quality degradation is estimated by quantifying the divergence between such distributions of the reference image and those of the distorted image. Experimental results demonstrate that the proposed method outperforms other state-of-the-art approaches in consideration of not only accuracy that is consistent with human subjective evaluation, but also robustness and stability across different distortion types and various public databases. It provides a promising choice for image quality assessment development.

Publication: IEICE TRANSACTIONS on Information Vol.E100-D No.6 pp.1303-1315

Publication Date: 2017/06/01

Publicized: 2017/03/16

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2016EDP7244

Type of Manuscript: PAPER

Category: Pattern Recognition

Authors

Yong DING
  Zhejiang University
Xinyu ZHAO
  Zhejiang University
Zhi ZHANG
  Lund University
Hang DAI
  University of York

Keyword

image quality assessment, image quality degradation, local pattern representation, feature extraction, visual perception

Cite this

Copy

Yong DING, Xinyu ZHAO, Zhi ZHANG, Hang DAI, "Image Quality Assessment Based on Multi-Order Local Features Description, Modeling and Quantification" in IEICE TRANSACTIONS on Information, vol. E100-D, no. 6, pp. 1303-1315, June 2017, doi: 10.1587/transinf.2016EDP7244.
Abstract: Image quality assessment (IQA) plays an important role in quality monitoring, evaluation and optimization for image processing systems. However, current quality-aware feature extraction methods for IQA can hardly balance accuracy and complexity. This paper introduces multi-order local description into image quality assessment for feature extraction. The first-order structure derivative and high-order discriminative information are integrated into local pattern representation to serve as the quality-aware features. Then joint distributions of the local pattern representation are modeled by spatially enhanced histogram. Finally, the image quality degradation is estimated by quantifying the divergence between such distributions of the reference image and those of the distorted image. Experimental results demonstrate that the proposed method outperforms other state-of-the-art approaches in consideration of not only accuracy that is consistent with human subjective evaluation, but also robustness and stability across different distortion types and various public databases. It provides a promising choice for image quality assessment development.
URL: https://globals.ieice.org/en_transactions/information/10.1587/transinf.2016EDP7244/_p

Copy

@ARTICLE{e100-d_6_1303,
author={Yong DING, Xinyu ZHAO, Zhi ZHANG, Hang DAI, },
journal={IEICE TRANSACTIONS on Information},
title={Image Quality Assessment Based on Multi-Order Local Features Description, Modeling and Quantification},
year={2017},
volume={E100-D},
number={6},
pages={1303-1315},
abstract={Image quality assessment (IQA) plays an important role in quality monitoring, evaluation and optimization for image processing systems. However, current quality-aware feature extraction methods for IQA can hardly balance accuracy and complexity. This paper introduces multi-order local description into image quality assessment for feature extraction. The first-order structure derivative and high-order discriminative information are integrated into local pattern representation to serve as the quality-aware features. Then joint distributions of the local pattern representation are modeled by spatially enhanced histogram. Finally, the image quality degradation is estimated by quantifying the divergence between such distributions of the reference image and those of the distorted image. Experimental results demonstrate that the proposed method outperforms other state-of-the-art approaches in consideration of not only accuracy that is consistent with human subjective evaluation, but also robustness and stability across different distortion types and various public databases. It provides a promising choice for image quality assessment development.},
keywords={},
doi={10.1587/transinf.2016EDP7244},
ISSN={1745-1361},
month={June},}

Copy

TY - JOUR
TI - Image Quality Assessment Based on Multi-Order Local Features Description, Modeling and Quantification
T2 - IEICE TRANSACTIONS on Information
SP - 1303
EP - 1315
AU - Yong DING
AU - Xinyu ZHAO
AU - Zhi ZHANG
AU - Hang DAI
PY - 2017
DO - 10.1587/transinf.2016EDP7244
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E100-D
IS - 6
JA - IEICE TRANSACTIONS on Information
Y1 - June 2017
AB - Image quality assessment (IQA) plays an important role in quality monitoring, evaluation and optimization for image processing systems. However, current quality-aware feature extraction methods for IQA can hardly balance accuracy and complexity. This paper introduces multi-order local description into image quality assessment for feature extraction. The first-order structure derivative and high-order discriminative information are integrated into local pattern representation to serve as the quality-aware features. Then joint distributions of the local pattern representation are modeled by spatially enhanced histogram. Finally, the image quality degradation is estimated by quantifying the divergence between such distributions of the reference image and those of the distorted image. Experimental results demonstrate that the proposed method outperforms other state-of-the-art approaches in consideration of not only accuracy that is consistent with human subjective evaluation, but also robustness and stability across different distortion types and various public databases. It provides a promising choice for image quality assessment development.
ER -