Title :
Image data compression using a self-organizing neural network with adaptive thresholds
Author :
Thacore, Sharad ; Pang, Vincent ; Palaniswami, M. ; Bairaktaris, Dimitrios
Author_Institution :
Dept. of Electr. Electron. Eng., Melbourne Univ., Parkville, Vic., Australia
Abstract :
Describes a novel neural network architecture which, when applied to image data compression, is capable of real-time, one shot, vector quantization. The major feature of this system is the utilization of an adaptive threshold mechanism. The architecture comprises a two-layer network and a winner-take-all cluster with adaptive thresholds. This system was used to generate a codebook for digital images
Keywords :
data compression; encoding; neural nets; picture processing; quantisation; adaptive thresholds; codebook; digital images; image data compression; self-organizing neural network; two-layer network; vector quantization; winner-take-all cluster; Adaptive systems; Biomedical engineering; Biomedical imaging; Data compression; Data engineering; Electronic mail; Image coding; Neural networks; Organizing; Vector quantization;
Conference_Titel :
Neural Networks, 1991. 1991 IEEE International Joint Conference on
Print_ISBN :
0-7803-0227-3
DOI :
10.1109/IJCNN.1991.170473
