Title :
Dynamic bit allocation in image coding using a Self-Organizing Map with Learning Vector Quantization
Author :
Neto, João Souza ; Neto, Sebastião Do Nascimento ; Nascimento, F.A.deO.
Author_Institution :
Engenharia Mecanica, Brazil
Abstract :
A Self-Organizing Map (SOM) Neural Network for dynamic bit allocation in Adaptive Image Transform Coding is presented. The results shown in this paper are for nets with 30, 96 and 128 neurons in the input layer and 100 (10×10) neurons in the competition layer. The Learning Vector Quantization LVQ1 algorithm was used to enhance the clustering in the map
Keywords :
adaptive codes; image coding; learning (artificial intelligence); self-organising feature maps; transform coding; vector quantisation; LVQ1 algorithm; adaptive image transform coding; clustering; dynamic bit allocation; learning vector quantization; self-organizing map neural network; Bit rate; Clustering algorithms; Electronic mail; Image coding; Image sampling; Iterative algorithms; Neurons; Organizing; Signal to noise ratio; Vector quantization;
Conference_Titel :
Circuits and Systems, 1995., Proceedings., Proceedings of the 38th Midwest Symposium on
Conference_Location :
Rio de Janeiro
Print_ISBN :
0-7803-2972-4
DOI :
10.1109/MWSCAS.1995.510224
