Affordable Access

Publisher Website

No-reference image quality assessment in curvelet domain

Authors
Journal
Signal Processing Image Communication
0923-5965
Publisher
Elsevier
Volume
29
Issue
4
Identifiers
DOI: 10.1016/j.image.2014.02.004
Keywords
  • Image Quality Assessment (Iqa)
  • No Reference (Nr)
  • Curvelet
  • Natural Scene Statistics (Nss)
  • Support Vector Machine (Svm)
Disciplines
  • Computer Science

Abstract

Abstract We study the efficacy of utilizing a powerful image descriptor, the curvelet transform, to learn a no-reference (NR) image quality assessment (IQA) model. A set of statistical features are extracted from a computed image curvelet representation, including the coordinates of the maxima of the log-histograms of the curvelet coefficients values, and the energy distributions of both orientation and scale in the curvelet domain. Our results indicate that these features are sensitive to the presence and severity of image distortion. Operating within a 2-stage framework of distortion classification followed by quality assessment, we train an image distortion and quality prediction engine using a support vector machine (SVM). The resulting algorithm, dubbed CurveletQA for short, was tested on the LIVE IQA database and compared to state-of-the-art NR/FR IQA algorithms. We found that CurveletQA correlates well with human subjective opinions of image quality, delivering performance that is competitive with popular full-reference (FR) IQA algorithms such as SSIM, and with top-performing NR IQA models. At the same time, CurveletQA has a relatively low complexity.

There are no comments yet on this publication. Be the first to share your thoughts.

Statistics

Seen <100 times
0 Comments

More articles like this

No-reference image quality assessment in the spati...

on IEEE transactions on image pro... December 2012

No-reference image quality assessment through the...

on Journal of the Optical Society... Oct 01, 2012
More articles like this..