Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

ICIP 2017 Paper #2679: THE DIVISIVE NORMALIZATION TRANSFORM BASED REDUCED-REFERENCE IMAGE QUALITY ASSESSMENT IN THE SHEARLET DOMAIN

Abstract: 

Reduced-reference (RR) image quality assessment (IQA)metric aims to employ less partial information about the original reference image to achieve higher evaluation accuracy. In this paper, we propose a novel RRIQA metric based on the divisive normalization transform (DNT) in the discrete nonseparable shearlet transform (DNST) domain. In this metric, the coefficients in the DNST domain are normalized employing the Gaussian scale mixture statistical model, and then the marginal distribution of the coefficients changes into approximate Gaussian distribution. A set of statistical features is extracted from DNT-domain representations of the reference and distorted images, respectively. The weighting of these features is performed based on the characteristics of the human visual system. Structural similarity comparison of these features is conducted as an objective quality score of the distorted image. The proposed
metric is evaluated on the public LIVE database and demonstrates fairly good performance across a wide range of
image distortions.

up
0 users have voted:

Paper Details

Authors:
Wu Dong;Hongxia Bie;Likun Lu;Yeli Li
Submitted On:
11 September 2017 - 7:42am
Short Link:
Type:
Poster
Event:
Presenter's Name:
Wu Dong
Paper Code:
2679
Document Year:
2017
Cite

Document Files

THE DIVISIVE NORMALIZATION TRANSFORM BASED REDUCED-REFERENCE IMAGE QUALITY ASSESSMENT IN THE SHEARLET DOMAIN

(21 downloads)

Subscribe

[1] Wu Dong;Hongxia Bie;Likun Lu;Yeli Li, "ICIP 2017 Paper #2679: THE DIVISIVE NORMALIZATION TRANSFORM BASED REDUCED-REFERENCE IMAGE QUALITY ASSESSMENT IN THE SHEARLET DOMAIN", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1903. Accessed: Nov. 25, 2017.
@article{1903-17,
url = {http://sigport.org/1903},
author = {Wu Dong;Hongxia Bie;Likun Lu;Yeli Li },
publisher = {IEEE SigPort},
title = {ICIP 2017 Paper #2679: THE DIVISIVE NORMALIZATION TRANSFORM BASED REDUCED-REFERENCE IMAGE QUALITY ASSESSMENT IN THE SHEARLET DOMAIN},
year = {2017} }
TY - EJOUR
T1 - ICIP 2017 Paper #2679: THE DIVISIVE NORMALIZATION TRANSFORM BASED REDUCED-REFERENCE IMAGE QUALITY ASSESSMENT IN THE SHEARLET DOMAIN
AU - Wu Dong;Hongxia Bie;Likun Lu;Yeli Li
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1903
ER -
Wu Dong;Hongxia Bie;Likun Lu;Yeli Li. (2017). ICIP 2017 Paper #2679: THE DIVISIVE NORMALIZATION TRANSFORM BASED REDUCED-REFERENCE IMAGE QUALITY ASSESSMENT IN THE SHEARLET DOMAIN. IEEE SigPort. http://sigport.org/1903
Wu Dong;Hongxia Bie;Likun Lu;Yeli Li, 2017. ICIP 2017 Paper #2679: THE DIVISIVE NORMALIZATION TRANSFORM BASED REDUCED-REFERENCE IMAGE QUALITY ASSESSMENT IN THE SHEARLET DOMAIN. Available at: http://sigport.org/1903.
Wu Dong;Hongxia Bie;Likun Lu;Yeli Li. (2017). "ICIP 2017 Paper #2679: THE DIVISIVE NORMALIZATION TRANSFORM BASED REDUCED-REFERENCE IMAGE QUALITY ASSESSMENT IN THE SHEARLET DOMAIN." Web.
1. Wu Dong;Hongxia Bie;Likun Lu;Yeli Li. ICIP 2017 Paper #2679: THE DIVISIVE NORMALIZATION TRANSFORM BASED REDUCED-REFERENCE IMAGE QUALITY ASSESSMENT IN THE SHEARLET DOMAIN [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1903