Title :
Application of neural “gas” model in image compression
Author :
Zhang, Bai-ling ; Fu, Min-yue ; Yan, Hong
Author_Institution :
Dept. of Electr. & Comput. Eng., Newcastle Univ., NSW, Australia
Abstract :
We propose to apply a topology representing learning algorithm, the neural “gas” model, for obtaining topology ordered codebook for the vector quantization and exploit it on image compression. Compared with the well-known Kohonen´s self-organizing map, the neural “gas” model has several advantages, including faster convergence and higher signal-to-noise ratio in reconstruction. We illustrate some experimental results and discuss several relevant research issues
Keywords :
convergence; image processing; learning (artificial intelligence); network topology; neural nets; vector quantisation; codebook; convergence; image compression; learning algorithm; neural gas model; topology; vector quantization; Application software; Australia; Clustering algorithms; Convergence; Image coding; Image reconstruction; Image storage; Neurons; Topology; Vector quantization;
Conference_Titel :
Neural Networks Proceedings, 1998. IEEE World Congress on Computational Intelligence. The 1998 IEEE International Joint Conference on
Conference_Location :
Anchorage, AK
Print_ISBN :
0-7803-4859-1
DOI :
10.1109/IJCNN.1998.685891
