Image data compression with neural networks

Three efficient image coding schemes, based orb neural networks, have been developed in this thesis: (1) Neural network vector quantization (NNVQ). The main advantage of this new technology is that it can accomplish the complex encoding process much faster than the previous algorithms. Its properties are studied and demonstrated by simulations. (2) A adaptive NNVQ for image sequence coding. Simulation experiments have been carried out with 4 x 4 blocks of pixels from an image sequence consisting of 40 frames. At 0.67 bits/pixel, this scheme achieves good image quality suitable for videoconferencing systems; (3) Neural network prediction. This new prediction algorithm can exploit high-order statistics and nonlinear correlations which are so difficult to do with traditional linear prediction. At 1 bit/pixel, the one dimension neural network differential pulse code modulation (DPCM) offers 4-5 db advantages over the standard linear DPCM algorithm. At bit rate 0.51 bits/pixel, the two dimension adaptive neural network DPCM achieves 29.5 db for the 512 x 512 LENA image and there is little visible distortion in the reconstructed image. This performance is quite comparable to that of the best schemes known to date, while maintaining a much lower encoding complexity.