Artificial neural network visual model for image quality enhancement

An artificial neural network visual model is developed, which extracts mult i-scale edge features from the decompressed image and uses these visual fea tures 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 postprocessing of the J PEG and quadtree coding systems show that the proposed artificial neural ne twork visual model significantly enhances the quality of reconstructed imag es, both in terms of the objective eak signal-to-noise ratio and subjective visual assessment. (C) 2000 Elsevier Science B.V. All rights reserved.