A Novel Evolutionary Swarm Fuzzy Clustering Approach for Hyperspectral Imagery

In land cover assessment, classes often gradually change from one to another. Therefore, it is difficult to allocate sharp boundaries between different classes of interest. To overcome this issue and model such conditions, fuzzy techniques that resemble human reasoning have been proposed as alternat...

Full description

Saved in:
Bibliographic Details
Published in:IEEE journal of selected topics in applied earth observations and remote sensing Vol. 8; no. 6; pp. 2447 - 2456
Main Authors: Ghamisi, Pedram, Ali, Abder-Rahman, Couceiro, Micael S., Benediktsson, Jon Atli
Format: Journal Article
Language:English
Published: IEEE 01.06.2015
Subjects:
Accuracy
Clustering
Clustering algorithms
Clustering methods
fractional order Darwinian particle swarm optimization (FODPSO)
fuzzy C-means (FCM)
hyperspectral image analysis
Hyperspectral imaging
support vector machine (SVM) classifier
Support vector machines
Training
fuzzy C-means (FCM)
fractional order Darwinian particle swarm optimization (FODPSO)
support vector machine (SVM) classifier
Clustering
hyperspectral image analysis
ISSN:1939-1404, 2151-1535
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In land cover assessment, classes often gradually change from one to another. Therefore, it is difficult to allocate sharp boundaries between different classes of interest. To overcome this issue and model such conditions, fuzzy techniques that resemble human reasoning have been proposed as alternatives. Fuzzy C-means is the most common fuzzy clustering technique, but its concept is based on a local search mechanism and its convergence rate is rather slow, especially considering high-dimensional problems (e.g., in processing of hyperspectral images). Here, in order to address those shortcomings of hard approaches, a new approach is proposed, i.e., fuzzy C-means which is optimized by fractional order Darwinian particle swarm optimization. In addition, to speed up the clustering process, the histogram of image intensities is used during the clustering process instead of the raw image data. Furthermore, the proposed clustering approach is combined with support vector machine classification to accurately classify hyperspectral images. The new classification framework is applied on two well-known hyperspectral data sets; Indian Pines and Salinas. Experimental results confirm that the proposed swarm-based clustering approach can group hyperspectral images accurately in a time-efficient manner compared to other existing clustering techniques.
ISSN:1939-1404
2151-1535
DOI:10.1109/JSTARS.2015.2398835