Estudio de dos estructuras neuronales feedforward para la compresión de imágenes digitales

This paper shows and explains the process implemented for the development of feed- forward neural networks with the aim of compress digital image color. It sets oul sorne traditional techniques and develops tvvo topologies to implement feed forward. During the development of networks, fue items that are considered: number of layers, number of neurons, image type, size and munber of blocks to train, to optimize performance during final training. It also discusses the standard quality of the image obtained, as peak signal noise relation (PSNR) and cornpression, which typically obtain values above 35dB in terms of PSNR and 2 bits per pixel in gray or 3 bpp color images, with maximum time of 3 seconds for images less than I mega pixel. Finally out some dravvbacks and presents conclusions of this type of compression.