A new technique for progressive image transmission (PIT) is presented that uses a self-supervised back-propagation neural network discrete cosine transform. The transmission sequence is determined using a back-propagation neural network (BPNN) feature importance function. Simulation results show that the PIT system can be successfully implemented using BPNN. Very good intermediate images are obtained at reasonable bit rates.
K. R. Rao,
Michael T. Manry,
"Progressive image transmission using a self-supervised back-propagation neural network," Journal of Electronic Imaging 1(1), (1 January 1992). https://doi.org/10.1117/12.55176