Title :
Neural networks-based image compression system
Author :
Charif, H. Nait ; Salam, Fathi M.
Author_Institution :
Ecole Superieure de Technologie, Univ. Mohammed I, Oujda, Morocco
Abstract :
The paper describes a practical and effective image compression system based on multilayer neural networks. The proposed system consists of two multilayer neural networks that compress the image in two stages. The first network compresses the image, and the second network compressed the error (i.e. the difference between the reconstructed and the original images). A comparison in performance sample images shows that the new system improves the image quality when 16×16-subimages with compression ratio of 16:1. Sample simulation results show the effectiveness of the proposed architecture
Keywords :
data compression; image coding; neural nets; image compression; multilayer neural network; Computer errors; Computer networks; Image coding; Image quality; Image reconstruction; Image storage; Multi-layer neural network; Neural networks; Redundancy; Teleconferencing;
Conference_Titel :
Circuits and Systems, 2000. Proceedings of the 43rd IEEE Midwest Symposium on
Conference_Location :
Lansing, MI
Print_ISBN :
0-7803-6475-9
DOI :
10.1109/MWSCAS.2000.952887
