C-DIIVINE: No-reference image quality assessment based on local magnitude and phase statistics of natural scenes

• Published in: Signal processing. Image communication 2014-08, Vol.29 (7), p.725-747
• Main Authors: Zhang, Yi, Moorthy, Anush K., Chandler, Damon M., Bovik, Alan C.
• Format: Article
• Language: English
• Subjects: Algorithms; Assessments; Complex Gaussian scale mixture; Complex wavelet transform; Distortion; Image quality; Image quality assessment; Mathematical models; Relative phase; Statistics; Wavelet
• ISSN: 0923-5965; 1879-2677
• DOI: 10.1016/j.image.2014.05.004

It is widely known that the wavelet coefficients of natural scenes possess certain statistical regularities which can be affected by the presence of distortions. The DIIVINE (Distortion Identification-based Image Verity and Integrity Evaluation) algorithm is a successful no-reference image quality assessment (NR IQA) algorithm, which estimates quality based on changes in these regularities. However, DIIVINE operates based on real-valued wavelet coefficients, whereas the visual appearance of an image can be strongly determined by both the magnitude and phase information. In this paper, we present a complex extension of the DIIVINE algorithm (called C-DIIVINE), which blindly assesses image quality based on the complex Gaussian scale mixture model corresponding to the complex version of the steerable pyramid wavelet transform. Specifically, we applied three commonly used distribution models to fit the statistics of the wavelet coefficients: (1) the complex generalized Gaussian distribution is used to model the wavelet coefficient magnitudes, (2) the generalized Gaussian distribution is used to model the coefficients׳ relative magnitudes, and (3) the wrapped Cauchy distribution is used to model the coefficients׳ relative phases. All these distributions have characteristic shapes that are consistent across different natural images but change significantly in the presence of distortions. We also employ the complex wavelet structural similarity index to measure degradation of the correlations across image scales, which serves as an important indicator of the subbands׳ energy distribution and the loss of alignment of local spectral components contributing to image structure. Experimental results show that these complex extensions allow C-DIIVINE to yield a substantial improvement in predictive performance as compared to its predecessor, and highly competitive performance relative to other recent no-reference algorithms. •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.