Share Email Print

Proceedings Paper

An algorithm for no-reference image quality assessment based on log-derivative statistics of natural scenes
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

In this paper, we propose a new method for blind/no-reference image quality assessment based on the log- derivative statistics of natural scenes. The new method, called DErivative Statistics-based Image QUality Eval- uator (DESIQUE), extracts image quality-related statistical features at two image scales in both the spatial and frequency domains, upon which a two-stage framework is employed to evaluate image quality. In the spatial domain, normalized luminance values of an image are modeled in two ways: point-wise based statistics for sin- gle pixel values and pairwise-based log-derivative statistics for the relationship of pixel pairs. In the frequency domain, log-Gabor filters are used to extract the high frequency component of an image, which is also modeled by the log-derivative statistics. All of these statistics are characterized by a generalized Gaussian distribution model, the parameters of which form the underlying features of the proposed method. Experiment results show that DESIQUE not only leads to considerable performance improvements, but also maintains high computational efficiency.

Paper Details

Date Published: 4 February 2013
PDF: 10 pages
Proc. SPIE 8653, Image Quality and System Performance X, 86530J (4 February 2013); doi: 10.1117/12.2001342
Show Author Affiliations
Yi Zhang, Oklahoma State Univ. (United States)
Damon M. Chandler, Oklahoma State Univ. (United States)

Published in SPIE Proceedings Vol. 8653:
Image Quality and System Performance X
Peter D. Burns; Sophie Triantaphillidou, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?