A modified method for codebook design with neural network in VQ sed image compression

Author

Hatami, S. ; Yazdanpanah, M.J. ; Forozandeh, B. ; Fatemi, O.

Author_Institution

Dept. of Electr. & Comput. Eng., Tehran Univ., Iran

Volume

2

fYear

2003

Abstract

The increased demands for image storage in computer systems and transmission in communication systems have magnified the importance of the demand for signal and image compression algorithms respectively. We have focused on Vector Quantization (VQ), as a well-known compression technique, which has been widely used in many speech and image coding systems. Algorithms such as LBG and SOM (a neural network (NN) algorithm) are used towards to find a proper codebook for a given training data in VQ. We have also computed a modified version SOM called SFS-HSOM. In this paper, we used four techniques to improve the reconstructed image quality up to 130% and to decrease training and encoding time.

Keywords

image coding; self-organising feature maps; vector quantisation; Kohonen self-organizing feature map; SFS-HSOM; codebook design; image coding; image compression; neural network algorithm; reconstructed image quality; Computer networks; Design methodology; Image coding; Image quality; Image reconstruction; Image storage; Neural networks; Speech coding; Training data; Vector quantization;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 2003. ISCAS '03. Proceedings of the 2003 International Symposium on

Print_ISBN

0-7803-7761-3

Type

conf

DOI

10.1109/ISCAS.2003.1206048

Filename

1206048