Title :
Predictive vector quantization using neural networks
Author :
Hashemi, M.R. ; Yeap, T.H. ; Panchanathan, S.
Author_Institution :
Dept. of Electr. Eng., Ottawa Univ., Ont., Canada
Abstract :
Proposes a new predicative vector quantization (PVQ) technique for image and video compression. This technique has been implemented using neural networks. A Kohonen self organized feature map is used to implement the vector quantizer, while a multilayer perceptron implements the predictor. The proposed technique provides a superior coding performance
Keywords :
multilayer perceptrons; prediction theory; self-organising feature maps; vector quantisation; video coding; Kohonen selforganized feature map; coding performance; image compression; multilayer perceptron; neural networks; predictive vector quantization; video compression; Computer networks; Image coding; Image reconstruction; Image storage; Laboratories; Neural networks; Pulse modulation; Speech; Transmitters; Vector quantization;
Conference_Titel :
Electrical and Computer Engineering, 1995. Canadian Conference on
Conference_Location :
Montreal, Que.
Print_ISBN :
0-7803-2766-7
DOI :
10.1109/CCECE.1995.526425
