Image quality assessment using full-parameter singular value decomposition

Rui Wang; Yu-zhu Cui; Yan Yuan

doi:10.1117/1.3579459

1 May 2011 Image quality assessment using full-parameter singular value decomposition

Rui Wang, Yu-zhu Cui, Yan Yuan

Author Affiliations +

Optical Engineering, Vol. 50, Issue 5, 057005 (May 2011). https://doi.org/10.1117/1.3579459

Abstract

A new full-parameter singular value decomposition-based image quality assessment (IQA) method, which aims at capturing the loss of structural content instead of measuring the distortion of pixel intensity value, is proposed. Both the singular vectors and the singular value are considered as features and weight for quantifying major information, respectively, to evaluate the distortion degree in images. Extensive validation experiments are conducted with two kinds of test images, one of which is the LIVE database supplied by the University of Texas and the other is created from our own simulation. The prediction performance of the presented metrics, such as accuracy, monotonicity, and consistency, is measured. The experiment results show that, compared to several state-of-the-art image quality metrics, the performance of the proposed IQA is in better alignment with the perception of the human visual system in predicting image quality, particularly when comparing images containing different types of distortions.

©(2011) Society of Photo-Optical Instrumentation Engineers (SPIE)

Citation Download Citation

Rui Wang, Yu-zhu Cui, and Yan Yuan "Image quality assessment using full-parameter singular value decomposition," Optical Engineering 50(5), 057005 (1 May 2011). https://doi.org/10.1117/1.3579459

Published: 1 May 2011

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available