|
Abstract : |
A new neural-network data compression method is presented. The work extends the use of two-layer neural networks to multilayer networks, Results show the performance superiority of multilayer neural networks compared with that of the two-layer one, especially at high compression ratios. To overcome the long training time required for multilayered networks, a recently developed training algorithm has been used. A modfied feedback error is proposed to reduce further the training time and to enhance the image quality. Also, a redistribution of the grey levels in the training phase is proposed to make the minimisation of the mean-square error more related to the human-vision system., A new neural-network data compression method is presented. The work extends the use of two-layer neural networks to multilayer networks. The results show the performance superiority of multilayer neural networks compared with that of the two-layer one, especially at high compression ratios. To overcome the long training time required for multilayered networks, a previously developed training algorithm has been used. A modified feedback error is proposed to reduce further the training time and to enhance the image quality. Also, a redistribution of the grey levels in the training phase is proposed to make the minimisation of the mean-square error more related to the human-vision system, |
