Pattern Recognition and Image Analysis

, Volume 20, Issue 3, pp 286–292

Wavelet-based directional structural distortion model for image quality assessment

Representation, Processing, Analysis, and Understanding of Images

DOI: 10.1134/S1054661810030041

Cite this article as:
Cheng, G., Cheng, L. & Li, Y. Pattern Recognit. Image Anal. (2010) 20: 286. doi:10.1134/S1054661810030041


It is a challenging work to find an efficient metric of image quality assessment, which is an important problem for many image processing tasks. In this paper, we propose a novel wavelet-based directional structural distortion model for image quality assessment, which explores the geometric structural features of natural image. The experimental results upon image database show that our proposed method is in accordance with characteristic of human visual system and has better consistency with the subjective assessment of human beings than current image quality assessment algorithms.

Key words

Image quality assessment Human visual system Wavelet transform Directional structural similarity 

Copyright information

© Pleiades Publishing, Ltd. 2010

Authors and Affiliations

  1. 1.School of ScienceNational University of Defense TechnologyChangsha, HunanChina
  2. 2.Department of MathematicsNational University of SingaporeSingaporeSingapore

Personalised recommendations