Adaptive feature-specific spectral imaging

P. A. Jansen; M. J. Dunlop; D. R. Golish; M. E. Gehm

doi:10.1117/12.918856

Adaptive feature-specific spectral imaging

P. A. Jansen, M. J. Dunlop, D. R. Golish, M. E. Gehm

Information, School of

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

2 Scopus citations

Abstract

We present an architecture for rapid spectral classification in spectral imaging applications. By making use of knowledge gained in prior measurements, our spectral imaging system is able to design adaptive feature-specific measurement kernels that selectively attend to the portions of a spectrum that contain useful classification information. With measurement kernels designed using a probabilistically-weighted version of principal component analysis, simulations predict an orders-of-magnitude reduction in classification error rates. We report on our latest simulation results, as well as an experimental prototype currently under construction.

Original language	English (US)
Title of host publication	Compressive Sensing
DOIs	https://doi.org/10.1117/12.918856
State	Published - 2012
Event	Compressive Sensing - Baltimore, MD, United States Duration: Apr 26 2012 → Apr 27 2012

Publication series

Name	Proceedings of SPIE - The International Society for Optical Engineering
Volume	8365
ISSN (Print)	0277-786X

Other

Other	Compressive Sensing
Country/Territory	United States
City	Baltimore, MD
Period	4/26/12 → 4/27/12

Keywords

Adaptive optics
Computational sensing
Spectral imaging

ASJC Scopus subject areas

Electronic, Optical and Magnetic Materials
Condensed Matter Physics
Computer Science Applications
Applied Mathematics
Electrical and Electronic Engineering

Access to Document

10.1117/12.918856

Cite this

@inproceedings{13eec862563e40daa107c7a370093c22,

title = "Adaptive feature-specific spectral imaging",

abstract = "We present an architecture for rapid spectral classification in spectral imaging applications. By making use of knowledge gained in prior measurements, our spectral imaging system is able to design adaptive feature-specific measurement kernels that selectively attend to the portions of a spectrum that contain useful classification information. With measurement kernels designed using a probabilistically-weighted version of principal component analysis, simulations predict an orders-of-magnitude reduction in classification error rates. We report on our latest simulation results, as well as an experimental prototype currently under construction.",

keywords = "Adaptive optics, Computational sensing, Spectral imaging",

author = "Jansen, {P. A.} and Dunlop, {M. J.} and Golish, {D. R.} and Gehm, {M. E.}",

year = "2012",

doi = "10.1117/12.918856",

language = "English (US)",

isbn = "9780819490438",

series = "Proceedings of SPIE - The International Society for Optical Engineering",

booktitle = "Compressive Sensing",

note = "Compressive Sensing ; Conference date: 26-04-2012 Through 27-04-2012",

}

TY - GEN

T1 - Adaptive feature-specific spectral imaging

AU - Jansen, P. A.

AU - Dunlop, M. J.

AU - Golish, D. R.

AU - Gehm, M. E.

PY - 2012

Y1 - 2012

N2 - We present an architecture for rapid spectral classification in spectral imaging applications. By making use of knowledge gained in prior measurements, our spectral imaging system is able to design adaptive feature-specific measurement kernels that selectively attend to the portions of a spectrum that contain useful classification information. With measurement kernels designed using a probabilistically-weighted version of principal component analysis, simulations predict an orders-of-magnitude reduction in classification error rates. We report on our latest simulation results, as well as an experimental prototype currently under construction.

AB - We present an architecture for rapid spectral classification in spectral imaging applications. By making use of knowledge gained in prior measurements, our spectral imaging system is able to design adaptive feature-specific measurement kernels that selectively attend to the portions of a spectrum that contain useful classification information. With measurement kernels designed using a probabilistically-weighted version of principal component analysis, simulations predict an orders-of-magnitude reduction in classification error rates. We report on our latest simulation results, as well as an experimental prototype currently under construction.

KW - Adaptive optics

KW - Computational sensing

KW - Spectral imaging

UR - http://www.scopus.com/inward/record.url?scp=84863887644&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84863887644&partnerID=8YFLogxK

U2 - 10.1117/12.918856

DO - 10.1117/12.918856

M3 - Conference contribution

AN - SCOPUS:84863887644

SN - 9780819490438

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - Compressive Sensing

T2 - Compressive Sensing

Y2 - 26 April 2012 through 27 April 2012

ER -

Adaptive feature-specific spectral imaging

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this