A No Reference Image Quality Metric for Blur and Ringing Effect based on a Neural Weighting Scheme

No Reference Image Quality Metrics proposed in the literature are generally developed for specific degradations, limiting thus their application. To overcome this limitation, we propose in this study a NR-IQM for ringing and blur distortions based on a neural weighting scheme. For a given image, we first estimate the level of blur and ringing degradations contained in an image using an Artificial Neural Networks (ANN) model. Then, the final index quality is given by combining blur and ringing measures by using the estimated weights through the learning process. The obtained results are promising.