Share Email Print
cover

Proceedings Paper

Blind image quality assessment without training on human opinion scores
Author(s): Anish Mittal; Rajiv Soundararajan; Gautam S. Muralidhar; Alan C. Bovik; Joydeep Ghosh
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

We propose a family of image quality assessment (IQA) models based on natural scene statistics (NSS), that can predict the subjective quality of a distorted image without reference to a corresponding distortionless image, and without any training results on human opinion scores of distorted images. These `completely blind' models compete well with standard non-blind image quality indices in terms of subjective predictive performance when tested on the large publicly available `LIVE' Image Quality database.

Paper Details

Date Published: 14 March 2013
PDF: 7 pages
Proc. SPIE 8651, Human Vision and Electronic Imaging XVIII, 86510T (14 March 2013); doi: 10.1117/12.981761
Show Author Affiliations
Anish Mittal, The Univ. of Texas at Austin (United States)
Rajiv Soundararajan, The Univ. of Texas at Austin (United States)
Gautam S. Muralidhar, The Univ. of Texas at Austin (United States)
Alan C. Bovik, The Univ. of Texas at Austin (United States)
Joydeep Ghosh, The Univ. of Texas at Austin (United States)


Published in SPIE Proceedings Vol. 8651:
Human Vision and Electronic Imaging XVIII
Bernice E. Rogowitz; Thrasyvoulos N. Pappas; Huib de Ridder, Editor(s)

© SPIE. Terms of Use
Back to Top