Title :
Adaptive Image Pyramidal Representation
Author :
Cherkashyn, Valeriy ; Kountchev, Roumen ; He, Dong-Chen ; Kountcheva, Roumiana
Author_Institution :
CARTEL, Univ. de Sherbrooke, Sherbrooke, QC
Abstract :
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.
Keywords :
backpropagation; data compression; image coding; image representation; neural nets; JPEG2000; adaptive image pyramidal representation; error back propagation; image compression; inverse difference pyramid; neural networks; Artificial neural networks; Discrete cosine transforms; Discrete wavelet transforms; Fractals; Image coding; Image representation; Image restoration; Neural networks; Transform coding; Vector quantization; Image pyramidal decomposition; Image representation and compression; Neural networks;
Conference_Titel :
Signal Processing and Information Technology, 2008. ISSPIT 2008. IEEE International Symposium on
Conference_Location :
Sarajevo
Print_ISBN :
978-1-4244-3554-8
Electronic_ISBN :
978-1-4244-3555-5
DOI :
10.1109/ISSPIT.2008.4775650
