J4

• Original Articles • Previous Articles     Next Articles

A new method for reduced-reference image quality assessment

WANG Ti-sheng;GAO Xin-bo;LU Wen;LI Guang-dong
  

  1. (School of Electronic Engineering, Xidian Univ., Xi′an 710071, China)
  • Received:1900-01-01 Revised:1900-01-01 Online:2008-02-20 Published:2008-01-20
  • Contact: WANG Ti-sheng E-mail:wangts201@sohu.com

Abstract: Based on the characteristic that image distortion results in the change of visual sensitivity coefficients of image, a new reduced-reference (RR) image quality assessment metric is proposed. Contourlet is applied to extract the visual sensitivity coefficients of the image. Summarizing the difference of visual sensitivity coefficients between the distorted image and the reference image, we can get the measurement of the distorted image. Experimental results illustrate that the proposed method has a good consistency with the subjective assessment of human beings, and can reflect the visual perception of the image effectively.

Key words: reduced reference, image quality assessment, Contourlet

CLC Number: 

  • TN911.73