Vector quantizer of medical image using wavelet transform and enhanced neural network
Kwang-Baek Kim, Sung-Kwan Je, Gwang-Ha Kim · 2005
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.