Classification of SAR imagery using multiscale self-organizing network

  • Authors:

  • Xianbin Wen

  • Affiliations:

  • School of Math. and Information Science, Shandong University of Technology, Zibo, China

  • Venue:
  • ISNN'05 Proceedings of the Second international conference on Advances in neural networks - Volume Part II
  • Year:
  • 2005

Quantified Score

Hi-index 0.01

Visualization

Abstract

A multiscale self-organizing mixture network (MSOMN) is proposed for learning mixture multiscale autoregressive model of synthetic aperture radar (SAR) imagery. The MSOMN combines the multiscale method, the Kullback-Leibler information metric, the stochastic approximation method, and the selforganizing map structure. Updating of the parameters is limited to a small neighborhood around the winner that is based on maximum posterior probability. The network possesses a simple structure, and yields fast convergence, which is confirmed by experimental results of SAR images.