POST-PROCESSING OF CODED IMAGES BY NEURAL-NETWORK CANCELLATION OF THE UNMASKED NOISE

This paper presents a new application of neural networks for the post-processing of coded images. It is based on a model of the human visual system. The image affected by coding noise is decomposed into perceptual channel components. The image restoration stage is realized by filtering the perceptual components of the channels for which the noise power is not masked by the image power. This operation, referred as cancellation of the unmasked noise, is performed using a multi-layer perceptron (MLP) network. Different network structures have been considered for this purpose. Simulation results of the processing scheme show significant improvements in both visual and objective (SNR) quality for post-processed images affected by DCT or subband coding noise.