Reduced-Reference Image Quality Assessment Based on Discrete Cosine Transform Entropy

Yazhong ZHANG; Jinjian WU; Guangming SHI; Xuemei XIE; Yi NIU; Chunxiao FAN

doi:10.1587/transfun.E98.A.2642

Reduced-Reference Image Quality Assessment Based on Discrete Cosine Transform Entropy

Yazhong ZHANG, Jinjian WU, Guangming SHI, Xuemei XIE, Yi NIU, Chunxiao FAN

Full Text Views

0

Cite this

Summary :

Reduced-reference (RR) image quality assessment (IQA) algorithm aims to automatically evaluate the distorted image quality with partial reference data. The goal of RR IQA metric is to achieve higher quality prediction accuracy using less reference information. In this paper, we introduce a new RR IQA metric by quantifying the difference of discrete cosine transform (DCT) entropy features between the reference and distorted images. Neurophysiological evidences indicate that the human visual system presents different sensitivities to different frequency bands. Moreover, distortions on different bands result in individual quality degradations. Therefore, we suggest to calculate the information degradation on each band separately for quality assessment. The information degradations are firstly measured by the entropy difference of reorganized DCT coefficients. Then, the entropy differences on all bands are pooled to obtain the quality score. Experimental results on LIVE, CSIQ, TID2008, Toyama and IVC databases show that the proposed method performs highly consistent with human perception with limited reference data (8 values).

Publication: IEICE TRANSACTIONS on Fundamentals Vol.E98-A No.12 pp.2642-2649

Publication Date: 2015/12/01

Publicized

Online ISSN: 1745-1337

DOI: 10.1587/transfun.E98.A.2642

Type of Manuscript: PAPER

Category: Digital Signal Processing

Authors

Yazhong ZHANG
  Xidian University
Jinjian WU
  Xidian University
Guangming SHI
  Xidian University
Xuemei XIE
  Xidian University
Yi NIU
  Xidian University
Chunxiao FAN
  Xidian University

Keyword

reduced-reference, image quality assessment (IQA), human visual system (HVS), discrete cosine transform (DCT), entropy

Cite this

Copy

Yazhong ZHANG, Jinjian WU, Guangming SHI, Xuemei XIE, Yi NIU, Chunxiao FAN, "Reduced-Reference Image Quality Assessment Based on Discrete Cosine Transform Entropy" in IEICE TRANSACTIONS on Fundamentals, vol. E98-A, no. 12, pp. 2642-2649, December 2015, doi: 10.1587/transfun.E98.A.2642.
Abstract: Reduced-reference (RR) image quality assessment (IQA) algorithm aims to automatically evaluate the distorted image quality with partial reference data. The goal of RR IQA metric is to achieve higher quality prediction accuracy using less reference information. In this paper, we introduce a new RR IQA metric by quantifying the difference of discrete cosine transform (DCT) entropy features between the reference and distorted images. Neurophysiological evidences indicate that the human visual system presents different sensitivities to different frequency bands. Moreover, distortions on different bands result in individual quality degradations. Therefore, we suggest to calculate the information degradation on each band separately for quality assessment. The information degradations are firstly measured by the entropy difference of reorganized DCT coefficients. Then, the entropy differences on all bands are pooled to obtain the quality score. Experimental results on LIVE, CSIQ, TID2008, Toyama and IVC databases show that the proposed method performs highly consistent with human perception with limited reference data (8 values).
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.E98.A.2642/_p

Copy

@ARTICLE{e98-a_12_2642,
author={Yazhong ZHANG, Jinjian WU, Guangming SHI, Xuemei XIE, Yi NIU, Chunxiao FAN, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Reduced-Reference Image Quality Assessment Based on Discrete Cosine Transform Entropy},
year={2015},
volume={E98-A},
number={12},
pages={2642-2649},
abstract={Reduced-reference (RR) image quality assessment (IQA) algorithm aims to automatically evaluate the distorted image quality with partial reference data. The goal of RR IQA metric is to achieve higher quality prediction accuracy using less reference information. In this paper, we introduce a new RR IQA metric by quantifying the difference of discrete cosine transform (DCT) entropy features between the reference and distorted images. Neurophysiological evidences indicate that the human visual system presents different sensitivities to different frequency bands. Moreover, distortions on different bands result in individual quality degradations. Therefore, we suggest to calculate the information degradation on each band separately for quality assessment. The information degradations are firstly measured by the entropy difference of reorganized DCT coefficients. Then, the entropy differences on all bands are pooled to obtain the quality score. Experimental results on LIVE, CSIQ, TID2008, Toyama and IVC databases show that the proposed method performs highly consistent with human perception with limited reference data (8 values).},
keywords={},
doi={10.1587/transfun.E98.A.2642},
ISSN={1745-1337},
month={December},}

Copy

TY - JOUR
TI - Reduced-Reference Image Quality Assessment Based on Discrete Cosine Transform Entropy
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 2642
EP - 2649
AU - Yazhong ZHANG
AU - Jinjian WU
AU - Guangming SHI
AU - Xuemei XIE
AU - Yi NIU
AU - Chunxiao FAN
PY - 2015
DO - 10.1587/transfun.E98.A.2642
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E98-A
IS - 12
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - December 2015
AB - Reduced-reference (RR) image quality assessment (IQA) algorithm aims to automatically evaluate the distorted image quality with partial reference data. The goal of RR IQA metric is to achieve higher quality prediction accuracy using less reference information. In this paper, we introduce a new RR IQA metric by quantifying the difference of discrete cosine transform (DCT) entropy features between the reference and distorted images. Neurophysiological evidences indicate that the human visual system presents different sensitivities to different frequency bands. Moreover, distortions on different bands result in individual quality degradations. Therefore, we suggest to calculate the information degradation on each band separately for quality assessment. The information degradations are firstly measured by the entropy difference of reorganized DCT coefficients. Then, the entropy differences on all bands are pooled to obtain the quality score. Experimental results on LIVE, CSIQ, TID2008, Toyama and IVC databases show that the proposed method performs highly consistent with human perception with limited reference data (8 values).
ER -