Blind Image Quality Assessment designed by learning-based at- tributes selection

Christophe Charrier (1) , Abdelhakim Saadane (2) , Christine Fernandez-Maloigne (2)

1 Equipe SAFE - Laboratoire GREYC - UMR6072
2 XLIM-ASALI - Synthèse et analyse d'images

With the rapid growth of image processing technologies, objective Image Quality Assessment (IQA) is a topic where considerable research effort has been made over the last two decades. IQA algorithms based on image structure have been shown to correlate well with Mean Opinion Scores (MOS). No-Reference (NR) image quality metrics are of fundamental interest as they can be embedded in practical applications This paper deals with a new NR-IQA metric based on natural scenes statistics. It proposes to model the best correlated statistics of seven well known no-reference image quality algorithms by a MultiVariate Gaus-sian Distribution (MVGD). A part of LIVE database is used with the associated DMOS to fit the MVGD model, namely Model Image Quality Index (MIQI). Hence, the quality of a distorted image is given by the DMOS that maximizes the multivariate Gaussian probability density function. Experimental results demonstrate the method effectiveness for a wide variety of distortions.

Domaines: Traitement des images [eess.IV]

Christophe Charrier, Abdelhakim Saadane, Christine Fernandez-Maloigne. Blind Image Quality Assessment designed by learning-based at- tributes selection. 25th IS&T Color Imaging Conference, Sep 2017, Lillehammer, Norway. ⟨hal-01595950⟩