Multiscale modeling for classification of SAR imagery using hybrid EM algorithm and genetic algorithm

被引：0

作者：

Xianbin Wen a

机构：

来源：

Progress in Natural Science | 2009年 / 19卷 / 08期

基金：

中国国家自然科学基金;

关键词：

SAR imagery; Classification; Multiscale; Hybrid EM algorithm; Genetic algorithm;

D O I：

暂无

中图分类号：

TN957.52 [数据、图像处理及录取]; TP18 [人工智能理论];

学科分类号：

080904 ; 0810 ; 081001 ; 081002 ; 081104 ; 081105 ; 0812 ; 0825 ; 0835 ; 1405 ;

摘要：

A novel method that hybridizes genetic algorithm (GA) and expectation maximization (EM) algorithm for the classification of synthetic aperture radar (SAR) imagery is proposed by the finite Gaussian mixtures model (GMM) and multiscale autoregressive (MAR) model. This algorithm is capable of improving the global optimality and consistency of the classification performance. The experiments on the SAR images show that the proposed algorithm outperforms the standard EM method significantly in classification accuracy.

引用

页码：1033 / 1036

页数：4

共 5 条

[1]

A Multiresolution Approach to Discrimination in SAR Imagery. Irving W,Novak L,Willsky A. IEEE Tran. Aerosp. Electron. Syst . 1997

[2]

Hierarchical stochastic modeling of SAR imagery for classification/compression. Kim A,Kim H. IEEE Transactions on Signal Processing . 1999

[3]

Finite Mixture Models. McLachlan G,Peel D. . 2000

[4]

Multiscale classification and anomaly enhancement of SAR imagery. Fosgate C,,Irving WW,Karl W, et al. IEEE Transactions on Image Processing . 1997

[5]

Mixture multiscale autoregressive modeling of SAR imagery for classification. Wen XB,Tian Z. Electronics Letters . 2003

← 1 →