Loading...
Loading...

Go to the content (press return)

Improving wishart classification of polarimetric SAR data using the hopfield neural network optimization approach

Author
Pajares, G.; Lopez, C.; Sánchez, F.; Molina, I.
Type of activity
Journal article
Journal
Remote sensing
Date of publication
2012-11-19
Volume
4
Number
11
First page
3571
Last page
3595
DOI
https://doi.org/10.3390/rs4113571 Open in new window
Repository
http://hdl.handle.net/2117/87165 Open in new window
URL
http://www.mdpi.com/2072-4292/4/11/3571 Open in new window
Abstract
This paper proposes the optimization relaxation approach based on the analogue Hopfield Neural Network (HNN) for cluster refinement of pre-classified Polarimetric Synthetic Aperture Radar (PolSAR) image data. We consider the initial classification provided by the maximum-likelihood classifier based on the complex Wishart distribution, which is then supplied to the HNN optimization approach. The goal is to improve the classification results obtained by the Wishart approach. The classification imp...
Citation
Pajares, G., Lopez, C., Sánchez, F., Molina, I. Improving wishart classification of polarimetric SAR data using the hopfield neural network optimization approach. "Remote sensing", 19 Novembre 2012, vol. 4, núm. 11, p. 3571-3595.
Keywords
Hopfield neural networks, Image classification, Optimization, Polarimetric synthetic aperture radar (PolSAR), Wishart classifier
Group of research
RSLAB - Remote Sensing Lab

Participants

  • Pajares Martinsanz, Gonzalo  (author)
  • López Martínez, Carlos  (author)
  • Sánchez Lladó, Francisco Javier  (author)
  • Molina, Iñigo  (author)