Title :
Improved dynamic bit allocation in image coding using a self-organizing map with learning vector quantization
Author :
Souza Neto, J. ; Neto, Jo?£o Souza ; de O.Nascimento, F.A.
Author_Institution :
Dept. of Electr. Eng., Brasilia Univ., 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 :
image coding; self-organising feature maps; transform coding; vector quantisation; LVQ1 algorithm; adaptive image transform coding; dynamic bit allocation; image coding; learning vector quantization; self-organizing map; Artificial neural networks; Bit rate; Clustering algorithms; Image coding; Image sampling; Iterative algorithms; Neurons; Signal to noise ratio; Transform coding; Vector quantization;
Conference_Titel :
Neural Networks,1997., International Conference on
Print_ISBN :
0-7803-4122-8
DOI :
10.1109/ICNN.1997.614019
