DocumentCode :
1850318
Title :
Vector quantizer of medical image using wavelet transform and enhanced neural network
Author :
Kim, Kwang-Baek ; Je, Sung-Kwan ; Kim, Gwang-Ha
Author_Institution :
Dept. of Comput. Eng., Silla Univ., Busan, South Korea
fYear :
2005
fDate :
23-25 June 2005
Firstpage :
202
Lastpage :
207
Abstract :
Vector quantizer takes care of special image features like edges also and hence belongs to the class of quantizers known as second generation coders. This paper proposes a vector quantization using wavelet transform and enhanced SOM algorithm for medical image compression. We propose the enhanced self-organizing algorithm to improve the defects of SOM algorithm, which, at first, reflects the error between the winner node and the input vector to the weight adaptation by using the frequency of the winner node. Secondly, it adjusts the weight in proportion to the present weight change and the previous weight change as well. To reduce the blocking effect and Improve the resolution, we construct vectors by using wavelet transform and apply the enhanced SOM algorithm to them. Our experimental results show that the proposed method energizes the compression ratio and decompression ratio.
Keywords :
data compression; image coding; medical image processing; self-organising feature maps; vector quantisation; wavelet transforms; compression ratio; enhanced SOM algorithm; medical image compression; second generation coders; self-organizing algorithm; vector quantization; wavelet transform; Artificial neural networks; Biomedical engineering; Biomedical imaging; Computer networks; Frequency; Image coding; Image storage; Neural networks; Vector quantization; Wavelet transforms;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Enterprise networking and Computing in Healthcare Industry, 2005. HEALTHCOM 2005. Proceedings of 7th International Workshop on
Print_ISBN :
0-7803-8940-9
Type :
conf
DOI :
10.1109/HEALTH.2005.1500440
Filename :
1500440
Link To Document :
بازگشت