Adaptive Image Pyramidal Representation

New adaptive method for image compression based on pyramid decomposition with neural networks with error back propagation (BPNN) is presented in this paper. The processed image is divided in blocks and then each is compressed in the space of the hidden layers of 3-layer BPNNs, which build the so-called inverse difference pyramid. The results of the new method modeling are compared with these, obtained using the image compression standards JPEG and JPEG2000.