Improving Wishart Classification of Polarimetric SAR Data Using the Hopfield Neural Network Optimization Approach
Open Access
- 19 November 2012
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 4 (11), 3571-3595
- https://doi.org/10.3390/rs4113571
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 improvement is verified by computing a cluster separability coefficient and a measure of homogeneity within the clusters. During the HNN optimization process, for each iteration and for each pixel, two consistency coefficients are computed, taking into account two types of relations between the pixel under consideration and its corresponding neighbors. Based on these coefficients and on the information coming from the pixel itself, the pixel under study is re-classified. Different experiments are carried out to verify that the proposed approach outperforms other strategies, achieving the best results in terms of separability and a trade-off with the homogeneity preserving relevant structures in the image. The performance is also measured in terms of computational central processing unit (CPU) times.This publication has 27 references indexed in Scilit:
- Analysis by Wavelet Frames of Spatial Statistics in SAR Data for Characterizing Structural Properties of ForestsIEEE Transactions on Geoscience and Remote Sensing, 2008
- Unsupervised terrain classification preserving polarimetric scattering characteristicsIEEE Transactions on Geoscience and Remote Sensing, 2004
- Unsupervised classification of multifrequency and fully polarimetric SAR images based on the H/A/Alpha-Wishart classifierIEEE Transactions on Geoscience and Remote Sensing, 2001
- Unsupervised classification using polarimetric decomposition and the complex Wishart classifierIEEE Transactions on Geoscience and Remote Sensing, 1999
- Application of the H/A/alpha polarimetric decomposition theorem for land classificationPublished by SPIE-Intl Soc Optical Eng ,1997
- An entropy based classification scheme for land applications of polarimetric SARIEEE Transactions on Geoscience and Remote Sensing, 1997
- A review of target decomposition theorems in radar polarimetryIEEE Transactions on Geoscience and Remote Sensing, 1996
- Fuzzy classification of earth terrain covers using complex polarimetric SAR dataInternational Journal of Remote Sensing, 1996
- Classification of multi-look polarimetric SAR imagery based on complex Wishart distributionInternational Journal of Remote Sensing, 1994
- Application of neural networks to radar image classificationIEEE Transactions on Geoscience and Remote Sensing, 1994