Some recent results on hyperspectral image classification

C. A. Shah; P. Watanachaturaporn; P. K. Varshney; M. K. Arora

doi:10.1109/WARSD.2003.1295214

Some recent results on hyperspectral image classification

C. A. Shah, P. Watanachaturaporn, P. K. Varshney, M. K. Arora

Department of Electrical Engineering & Computer Science

Research output: Chapter in Book/Entry/Poem › Conference contribution

53 Scopus citations

Abstract

In this paper, we present a summary of our ongoing research on the classification of hyperspectral images. We are experimenting with both supervised and unsupervised algorithms. In particular, we have developed an unsupervised classification algorithm based on Independent Component Analysis (ICA). This algorithm is known as the ICA mixture model (ICAMM) algorithm and has shown promising results. In addition, we are investigating the use of Support Vector Machines (SVMs), a supervised approach for the classification of hyperspectral data. We have employed the Lagrangian optimization method and call our classifier the Lagrangian SVM (LSVM) classifier. Classification accuracy of these classifiers has been assessed using an error matrix based overall accuracy measure.

Original language	English (US)
Title of host publication	2003 IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	346-353
Number of pages	8
ISBN (Electronic)	0780383508, 9780780383500
DOIs	https://doi.org/10.1109/WARSD.2003.1295214
State	Published - 2004
Event	2003 IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data - Greenbelt, United States Duration: Oct 27 2003 → Oct 28 2003

Publication series

Name	2003 IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data

Other

Other	2003 IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data
Country/Territory	United States
City	Greenbelt
Period	10/27/03 → 10/28/03

Keywords

ICA mixture model
classification
hyperspectral images
independent componenet analysis
support vector machines

ASJC Scopus subject areas

Computer Networks and Communications

Access to Document

10.1109/WARSD.2003.1295214

Cite this

Shah, C. A., Watanachaturaporn, P., Varshney, P. K., & Arora, M. K. (2004). Some recent results on hyperspectral image classification. In 2003 IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data (pp. 346-353). Article 1295214 (2003 IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/WARSD.2003.1295214

Some recent results on hyperspectral image classification. / Shah, C. A.; Watanachaturaporn, P.; Varshney, P. K. et al.
2003 IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data. Institute of Electrical and Electronics Engineers Inc., 2004. p. 346-353 1295214 (2003 IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data).

Research output: Chapter in Book/Entry/Poem › Conference contribution

Shah, CA, Watanachaturaporn, P, Varshney, PK & Arora, MK 2004, Some recent results on hyperspectral image classification. in 2003 IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data., 1295214, 2003 IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data, Institute of Electrical and Electronics Engineers Inc., pp. 346-353, 2003 IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data, Greenbelt, United States, 10/27/03. https://doi.org/10.1109/WARSD.2003.1295214

Shah CA, Watanachaturaporn P, Varshney PK, Arora MK. Some recent results on hyperspectral image classification. In 2003 IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data. Institute of Electrical and Electronics Engineers Inc. 2004. p. 346-353. 1295214. (2003 IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data). doi: 10.1109/WARSD.2003.1295214

@inproceedings{e60a7454f41a48819a93439066facbd6,

title = "Some recent results on hyperspectral image classification",

abstract = "In this paper, we present a summary of our ongoing research on the classification of hyperspectral images. We are experimenting with both supervised and unsupervised algorithms. In particular, we have developed an unsupervised classification algorithm based on Independent Component Analysis (ICA). This algorithm is known as the ICA mixture model (ICAMM) algorithm and has shown promising results. In addition, we are investigating the use of Support Vector Machines (SVMs), a supervised approach for the classification of hyperspectral data. We have employed the Lagrangian optimization method and call our classifier the Lagrangian SVM (LSVM) classifier. Classification accuracy of these classifiers has been assessed using an error matrix based overall accuracy measure.",

keywords = "ICA mixture model, classification, hyperspectral images, independent componenet analysis, support vector machines",

author = "Shah, {C. A.} and P. Watanachaturaporn and Varshney, {P. K.} and Arora, {M. K.}",

note = "Publisher Copyright: {\textcopyright} 2004 IEEE.; 2003 IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data ; Conference date: 27-10-2003 Through 28-10-2003",

year = "2004",

doi = "10.1109/WARSD.2003.1295214",

language = "English (US)",

series = "2003 IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "346--353",

booktitle = "2003 IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data",

}

TY - GEN

T1 - Some recent results on hyperspectral image classification

AU - Shah, C. A.

AU - Watanachaturaporn, P.

AU - Varshney, P. K.

AU - Arora, M. K.

PY - 2004

Y1 - 2004

N2 - In this paper, we present a summary of our ongoing research on the classification of hyperspectral images. We are experimenting with both supervised and unsupervised algorithms. In particular, we have developed an unsupervised classification algorithm based on Independent Component Analysis (ICA). This algorithm is known as the ICA mixture model (ICAMM) algorithm and has shown promising results. In addition, we are investigating the use of Support Vector Machines (SVMs), a supervised approach for the classification of hyperspectral data. We have employed the Lagrangian optimization method and call our classifier the Lagrangian SVM (LSVM) classifier. Classification accuracy of these classifiers has been assessed using an error matrix based overall accuracy measure.

AB - In this paper, we present a summary of our ongoing research on the classification of hyperspectral images. We are experimenting with both supervised and unsupervised algorithms. In particular, we have developed an unsupervised classification algorithm based on Independent Component Analysis (ICA). This algorithm is known as the ICA mixture model (ICAMM) algorithm and has shown promising results. In addition, we are investigating the use of Support Vector Machines (SVMs), a supervised approach for the classification of hyperspectral data. We have employed the Lagrangian optimization method and call our classifier the Lagrangian SVM (LSVM) classifier. Classification accuracy of these classifiers has been assessed using an error matrix based overall accuracy measure.

KW - ICA mixture model

KW - classification

KW - hyperspectral images

KW - independent componenet analysis

KW - support vector machines

UR - http://www.scopus.com/inward/record.url?scp=84871449098&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84871449098&partnerID=8YFLogxK

U2 - 10.1109/WARSD.2003.1295214

DO - 10.1109/WARSD.2003.1295214

M3 - Conference contribution

AN - SCOPUS:84871449098

T3 - 2003 IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data

SP - 346

EP - 353

BT - 2003 IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2003 IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data

Y2 - 27 October 2003 through 28 October 2003

ER -

Some recent results on hyperspectral image classification

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this