Reduced-reference image quality metric based on statistic model in complex wavelet transform domain
| Autor: | Clency Perrine, Nanrun Zhou, Jianhua Wu, Yannis Pousset, Philippe Carré, Xinwen Xie |
|---|---|
| Přispěvatelé: | XLIM (XLIM), Université de Limoges (UNILIM)-Centre National de la Recherche Scientifique (CNRS), Nanchang University |
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
Wrapped Cauchy distribution
Image quality 020206 networking & telecommunications 02 engineering and technology Inverse Gaussian distribution symbols.namesake Wavelet Feature (computer vision) Signal Processing Metric (mathematics) 0202 electrical engineering electronic engineering information engineering symbols 020201 artificial intelligence & image processing [INFO]Computer Science [cs] Computer Vision and Pattern Recognition Electrical and Electronic Engineering Complex wavelet transform Divergence (statistics) Algorithm Software Mathematics |
| Zdroj: | Signal Processing: Image Communication Signal Processing: Image Communication, Elsevier, 2019, 74, pp.218-230. ⟨10.1016/j.image.2019.02.006⟩ |
| ISSN: | 0923-5965 1879-2677 |
| DOI: | 10.1016/j.image.2019.02.006⟩ |
| Popis: | A new Reduced-Reference (RR) image quality metric based on statistical models in the complex wavelet transform domain is proposed. The magnitude and the relative phase information of the complex wavelet coefficients is modeled by using probability density function, and a strategy based on the information criterion is proposed to optimally approximate the distribution. To further improve the accuracy of the metric, a comparison of the candidate models is studied, and the inverse Gaussian distribution and the wrapped Cauchy distribution are selected to model the magnitude and the relative phase distributions, respectively. The Kullback–Leibler divergence between the distributions of the reference image and the distorted one serves as the RR feature to measure the distortion. Finally, a generalized regression neural network is employed to map the RR feature into an objective score. Experimental studies confirmed that the proposed RR image quality metric is quality-aware and highly correlated with the human visual system. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect