LazySOM: Image Compression Using an Enhanced Self-Organizing Map
A self-organizing map (SOM), i.e. a congenital clustering algorithm, has a high compression ratio and produces high-quality reconstructed images, making it very suitable for generating image compression codebooks. However, SOMs incur heavy computation particularly when using large numbers of training samples. Thus, to speed up training, this investigation presents an enhanced SOM (named LazySOM) involving a hybrid algorithm combining LBG, SOM and Fast SOM. The proposed algorithm has a low computation cost, enabling the use of SOM with large numbers of training patterns. Simulations are performed to measure two indicators, PSNR and time cost, of the proposed LazySOM.
KeywordsImage compression vector quantization SOM
- 4.Kohonen, T.: Self-organizing map, Berlin (1995)Google Scholar
- 6.Madeiro, F., Vilar, R.M., Neto, B.G.A.: A Self-Organizing Algorithm for Image Compression. In: Proceedings of Vth Brazilian Symposium on Neural Networks, pp. 146–150 (1998)Google Scholar
- 8.Barbalho, M., Duarte, A., Neto, D., Costa, A.F., Netto, L.A.: Hierarchical SOM applied to image compression. In: Proceedings of International Joint Conference on Neural Networks, pp. 442–447 (2001)Google Scholar
- 10.Su, M.C., Liu, T.K., Chang, H.T.: Improving the self-organizing feature map algorithm using an efficient initialization scheme. Tamkang Journal of Science and Engineering 5(1), 35–48 (2002)Google Scholar
- 11.Tsai, C.-F., Jhuang, C.-A., Liu, C.-W.: Gray Image Compression Using New Hierarchical Self-Organizing Map Technique. In: International Conference on Innovative Computing, Information and Control, Paper No. 2858 (2008)Google Scholar