Journal of South China University of Technology (Natural Science Edition) ›› 2006, Vol. 34 ›› Issue (9): 22-25.

• Electronics, Communication & Automation Technology • Previous Articles     Next Articles

Gradient-Based Structural Similarity for Image Quality Assessmen

Yang Chun-ling  Kuang Kai-zhi  Chen Guan-hao  Xie Sheng-li   

  1. School of Electronic and Information Engineering,South China Univ.of Teeh.,Guangzhou 510640,Guangdong,China
  • Received:2005-11-21 Online:2006-09-25 Published:2006-09-25
  • Contact: 杨春玲(1970-)，女，副教授，主要从事图像和视频处理方面的研究 E-mail:eechlyang@scut.edu.cn
  • About author:杨春玲(1970-)，女，副教授，主要从事图像和视频处理方面的研究
  • Supported by:

    国家自然科学基金资助项目(60402015)；国家杰出青年自然科学基金资助项目(60325310)

PDF

4295

Abstract:

Although the SSIM (Structural Similarity)model,an assessment model of image quality based on the structural information,has been proved to be better than the PSNR(Peak Signal to Noise Ratio)or the MSE(Mean Square Error)model,there still remain some deficiencies in assessing badly blured images.In order to solve this prob-lem,this paper proposes a gradient-based structural similarity(GSSIM)model that takes the gradient as the main strut-tural information of an image.Experimental results show that the proposed GSSIM model is more consistent with human visual system and can assess the quality of blured images more precisely than the SSIM and PSNR (MSE)models.

Key words: image quality, assessment, structural similarity, gradient-based structural similarity, human visual system