Comparison of GENIE and conventional supervised classifiers for multispectral image feature extraction

Neal R. Harvey; James Theiler; Steven P. Brumby; Simon Perkins; John J. Szymanski; Jeffrey J. Bloch; Reid B. Porter; Mark Galassi; A. Cody Young

doi:10.1109/36.992801

Comparison of GENIE and conventional supervised classifiers for multispectral image feature extraction

Neal R. Harvey, James Theiler, Steven P. Brumby, Simon Perkins, John J. Szymanski, Jeffrey J. Bloch, Reid B. Porter, Mark Galassi, A. Cody Young

Research output: Contribution to journal › Article › peer-review

98 Scopus citations

Abstract

We have developed an automated feature detection/classification system, called GENetic Imagery Exploitation a (GENIE), which has been designed to generate image processing pipelines for a variety of feature detection/classification tasks. GENiE is a hybrid evolutionary algorithm that addresses the general problem of finding features of interest in multispectral remotely-sensed images. We describe our system in detail together with experiments involving comparisons of GENIE with several conventional supervised classification techniques, for a number of classification tasks using multispectral remotely sensed imagery.

Original language	English (US)
Pages (from-to)	393-404
Number of pages	12
Journal	IEEE Transactions on Geoscience and Remote Sensing
Volume	40
Issue number	2
DOIs	https://doi.org/10.1109/36.992801
State	Published - Feb 2002
Externally published	Yes

Keywords

Evolutionary algorithms
Genetic programming
Image processing
Multispectral imagery
Remote sensing
Supervised classification

ASJC Scopus subject areas

Electrical and Electronic Engineering
General Earth and Planetary Sciences

Access to Document

10.1109/36.992801

Cite this

@article{0b46ce43f84f4abd99fa94d1a2ad558c,

title = "Comparison of GENIE and conventional supervised classifiers for multispectral image feature extraction",

abstract = "We have developed an automated feature detection/classification system, called GENetic Imagery Exploitation a (GENIE), which has been designed to generate image processing pipelines for a variety of feature detection/classification tasks. GENiE is a hybrid evolutionary algorithm that addresses the general problem of finding features of interest in multispectral remotely-sensed images. We describe our system in detail together with experiments involving comparisons of GENIE with several conventional supervised classification techniques, for a number of classification tasks using multispectral remotely sensed imagery.",

keywords = "Evolutionary algorithms, Genetic programming, Image processing, Multispectral imagery, Remote sensing, Supervised classification",

author = "Harvey, {Neal R.} and James Theiler and Brumby, {Steven P.} and Simon Perkins and Szymanski, {John J.} and Bloch, {Jeffrey J.} and Porter, {Reid B.} and Mark Galassi and Young, {A. Cody}",

note = "Funding Information: Manuscript received January 23, 2001; revised June 29, 2001. This work was supported by the U.S. Departments of Energy and Defense. The authors are with the Los Alamos National Laboratory, Los Alamos, NM 87545 USA (e-mail: harve@lanl.gov). Publisher Item Identifier S 0196-2892(02)01565-6.",

year = "2002",

month = feb,

doi = "10.1109/36.992801",

language = "English (US)",

volume = "40",

pages = "393--404",

journal = "IEEE Transactions on Geoscience and Remote Sensing",

issn = "0196-2892",

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

number = "2",

}

TY - JOUR

T1 - Comparison of GENIE and conventional supervised classifiers for multispectral image feature extraction

AU - Harvey, Neal R.

AU - Theiler, James

AU - Brumby, Steven P.

AU - Perkins, Simon

AU - Szymanski, John J.

AU - Bloch, Jeffrey J.

AU - Porter, Reid B.

AU - Galassi, Mark

AU - Young, A. Cody

N1 - Funding Information: Manuscript received January 23, 2001; revised June 29, 2001. This work was supported by the U.S. Departments of Energy and Defense. The authors are with the Los Alamos National Laboratory, Los Alamos, NM 87545 USA (e-mail: harve@lanl.gov). Publisher Item Identifier S 0196-2892(02)01565-6.

PY - 2002/2

Y1 - 2002/2

N2 - We have developed an automated feature detection/classification system, called GENetic Imagery Exploitation a (GENIE), which has been designed to generate image processing pipelines for a variety of feature detection/classification tasks. GENiE is a hybrid evolutionary algorithm that addresses the general problem of finding features of interest in multispectral remotely-sensed images. We describe our system in detail together with experiments involving comparisons of GENIE with several conventional supervised classification techniques, for a number of classification tasks using multispectral remotely sensed imagery.

AB - We have developed an automated feature detection/classification system, called GENetic Imagery Exploitation a (GENIE), which has been designed to generate image processing pipelines for a variety of feature detection/classification tasks. GENiE is a hybrid evolutionary algorithm that addresses the general problem of finding features of interest in multispectral remotely-sensed images. We describe our system in detail together with experiments involving comparisons of GENIE with several conventional supervised classification techniques, for a number of classification tasks using multispectral remotely sensed imagery.

KW - Evolutionary algorithms

KW - Genetic programming

KW - Image processing

KW - Multispectral imagery

KW - Remote sensing

KW - Supervised classification

UR - http://www.scopus.com/inward/record.url?scp=0036477310&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036477310&partnerID=8YFLogxK

U2 - 10.1109/36.992801

DO - 10.1109/36.992801

M3 - Article

AN - SCOPUS:0036477310

SN - 0196-2892

VL - 40

SP - 393

EP - 404

JO - IEEE Transactions on Geoscience and Remote Sensing

JF - IEEE Transactions on Geoscience and Remote Sensing

IS - 2

ER -

Comparison of GENIE and conventional supervised classifiers for multispectral image feature extraction

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this