Artificial neural network visual model for image quality enhancement

An artiicial neural network visual model is developed, which extracts multi-scale edge features from the decompressed image and uses these visual features as input to estimate and compensate for the coding distortions. This provides a generic postprocessing technique that can be applied to all the main coding methods. Experimental results involving post-processing the JPEG and quadtree coding systems show that the proposed artiicial neural network visual model signiicantly enhances the quality of reconstructed images, both in terms of the objective peak signal to noise ratio and subjective visual assessment.