C-DIIVINE: No-reference image quality assessment based on local magnitude and phase statistics of natural scenes
作者:
Highlights:
• We model wavelet coefficients based on complex Gaussian scale mixture model.
• The coefficient magnitudes follow the complex generalized Gaussian distribution.
• The coefficient relative magnitudes follow the generalized Gaussian distribution.
• The coefficient relative phases follow the wrapped Cauchy distribution.
• Combined one- and two-stage frameworks are employed to predict image quality.
摘要
Highlights•We model wavelet coefficients based on complex Gaussian scale mixture model.•The coefficient magnitudes follow the complex generalized Gaussian distribution.•The coefficient relative magnitudes follow the generalized Gaussian distribution.•The coefficient relative phases follow the wrapped Cauchy distribution.•Combined one- and two-stage frameworks are employed to predict image quality.
论文关键词:Image quality assessment,Complex wavelet transform,Complex Gaussian scale mixture,Relative phase
论文评审过程:Received 26 September 2013, Revised 15 January 2014, Accepted 14 May 2014, Available online 28 May 2014.
论文官网地址:https://doi.org/10.1016/j.image.2014.05.004