Multiple Spectral-Spatial Classification Approach for Hyperspectral Data

A new multiple-classifier approach for spectral-spatial classification of hyperspectral images is proposed. Several classifiers are used independently to classify an image. For every pixel, if all the classifiers have assigned this pixel to the same class, the pixel is kept as a marker, i.e., a seed...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on geoscience and remote sensing 2010-11, Vol.48 (11), p.4122-4132
Main Authors: Tarabalka, Yuliya, Benediktsson, Jón Atli, Chanussot, Jocelyn, Tilton, James C
Format: Article
Language:English
Subjects:
Classification
Classifiers
Clustering algorithms
Computer Science
Forests
hyperspectral images
Hyperspectral imaging
Image Processing
Image segmentation
Markers
minimum spanning forest (MSF)
multiple classifiers (MCs)
Partitioning algorithms
Pixel
Pixels
Seeds
Segmentation
Spectra
Support vector machines
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:A new multiple-classifier approach for spectral-spatial classification of hyperspectral images is proposed. Several classifiers are used independently to classify an image. For every pixel, if all the classifiers have assigned this pixel to the same class, the pixel is kept as a marker, i.e., a seed of the spatial region with a corresponding class label. We propose to use spectral-spatial classifiers at the preliminary step of the marker-selection procedure, each of them combining the results of a pixelwise classification and a segmentation map. Different segmentation methods based on dissimilar principles lead to different classification results. Furthermore, a minimum spanning forest is built, where each tree is rooted on a classification-driven marker and forms a region in the spectral-spatial classification map. Experimental results are presented for two hyperspectral airborne images. The proposed method significantly improves classification accuracies when compared with previously proposed classification techniques.
ISSN:0196-2892
1558-0644
DOI:10.1109/TGRS.2010.2062526