Abstract | ||
---|---|---|
A self-organization neural network architecture is used to implement vector quantization for image compression. A modified self-organization algorithm, which is based on the frequency-sensitive cost function and centroid learning rule, is utilized to construct the codebooks. Performances of this frequency-sensitive self-organization network and a conventional algorithm for vector quantization are compared. The proposed method is quite efficient and can achieve near-optimal results. Good adaptivity for different statistics of source data can also be achieved |
Year | DOI | Venue |
---|---|---|
1994 | 10.1109/76.322995 | Circuits and Systems for Video Technology, IEEE Transactions |
Keywords | Field | DocType |
data compression,image coding,learning (artificial intelligence),self-organising feature maps,vector quantisation,adaptivity,centroid learning rule,codebooks,frequency-sensitive cost function,image compression,performance,self-organization networks,self-organization neural network architecture,source data,vector quantization | Computer vision,Pattern recognition,Computer science,Learning vector quantization,Vector quantization,Learning rule,Types of artificial neural networks,Artificial intelligence,Data compression,Neural gas,Centroid,Image compression | Journal |
Volume | Issue | ISSN |
4 | 5 | 1051-8215 |
Citations | PageRank | References |
24 | 2.38 | 8 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Oscal T-C Chen | 1 | 60 | 10.13 |
B. J. Sheu | 2 | 129 | 28.40 |
Wai-Chi Fang | 3 | 299 | 52.98 |