Encoding of Still Pictures by Wavelet Transform with Vector Quantization Using a Rough Fuzzy Neural Network

Shao-Han LIU  Jzau-Sheng LIN  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E86-D   No.9   pp.1896-1902
Publication Date: 2003/09/01
Online ISSN: 
DOI: 
Print ISSN: 0916-8532
Type of Manuscript: PAPER
Category: Image Processing, Image Pattern Recognition
Keyword: 
color image compression,  fuzzy Hopfield neural network,  wavelet transform,  rough set,  vector quantization,  

Full Text: PDF(1.2MB)>>
Buy this Article




Summary: 
In this paper color image compression using a fuzzy Hopfield-model net based on rough-set reasoning is created to generate optimal codebook based on Vector Quantization (VQ) in Discrete Wavelet Transform (DWT). The main purpose is to embed rough-set learning scheme into the fuzzy Hopfield network to construct a compression system named Rough Fuzzy Hopfield Net (RFHN). First a color image is decomposed into 3-D pyramid structure with various frequency bands. Then the RFHN is used to create different codebooks for various bands. The energy function of RFHN is defined as the upper- and lower-bound fuzzy membership grades between training samples and codevectors. Finally, near global-minimum codebooks in frequency domain can be obtained when the energy function converges to a stable state. Therefore, only 32/N pixels are selected as the training samples if a 3N-dimensional color image was used. In the simulation results, the proposed network not only reduces the consuming time but also preserves the compression performance.