Investigating face recognition from hyperspectral data: Impact of band extraction

Stefan A. Robila; Andrew LaChance; Shawna Ruff

doi:10.1117/12.817025

Investigating face recognition from hyperspectral data: Impact of band extraction

Stefan A. Robila, Andrew LaChance, Shawna Ruff

Computer Science

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

2 Scopus citations

Abstract

Among various biometrics measures used in human identification, face recognition, has the distinct advantage of not requiring the subjects collaboration. Hyperspectral data constitute a natural choice for expanding face recognition image fusion, especially since it may provide information beyond the normal visible range, thus exceeding the normal human sensing. In this paper we investigate algorithms that improve face recognition by extracting the 'best bands' according to various criteria such as decorrelation and statistical independence. The work expands on previous band extraction results and has the distinct advantage of being one of the first that combines spatial information (i.e. face characteristics) with spectral information.

Original language	English
Title of host publication	Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XV
Volume	7334
DOIs	https://doi.org/10.1117/12.817025
State	Published - 14 Sep 2009
Event	Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XV - Orlando, FL, United States Duration: 13 Apr 2009 → 16 Apr 2009

Other

Other	Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XV
Country/Territory	United States
City	Orlando, FL
Period	13/04/09 → 16/04/09

Keywords

Face recognition
Feature extraction
Hyperspectral data

Access to Document

10.1117/12.817025

Cite this

@inproceedings{d1c76f47481c4871b9592b5905b2056a,

title = "Investigating face recognition from hyperspectral data: Impact of band extraction",

abstract = "Among various biometrics measures used in human identification, face recognition, has the distinct advantage of not requiring the subjects collaboration. Hyperspectral data constitute a natural choice for expanding face recognition image fusion, especially since it may provide information beyond the normal visible range, thus exceeding the normal human sensing. In this paper we investigate algorithms that improve face recognition by extracting the 'best bands' according to various criteria such as decorrelation and statistical independence. The work expands on previous band extraction results and has the distinct advantage of being one of the first that combines spatial information (i.e. face characteristics) with spectral information.",

keywords = "Face recognition, Feature extraction, Hyperspectral data",

author = "Robila, {Stefan A.} and Andrew LaChance and Shawna Ruff",

year = "2009",

month = sep,

day = "14",

doi = "10.1117/12.817025",

language = "English",

isbn = "9780819476005",

volume = "7334",

booktitle = "Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XV",

note = "Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XV ; Conference date: 13-04-2009 Through 16-04-2009",

}

Robila, SA, LaChance, A & Ruff, S 2009, Investigating face recognition from hyperspectral data: Impact of band extraction. in Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XV. vol. 7334, 73341Y, Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XV, Orlando, FL, United States, 13/04/09. https://doi.org/10.1117/12.817025

TY - GEN

T1 - Investigating face recognition from hyperspectral data

T2 - Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XV

AU - Robila, Stefan A.

AU - LaChance, Andrew

AU - Ruff, Shawna

PY - 2009/9/14

Y1 - 2009/9/14

N2 - Among various biometrics measures used in human identification, face recognition, has the distinct advantage of not requiring the subjects collaboration. Hyperspectral data constitute a natural choice for expanding face recognition image fusion, especially since it may provide information beyond the normal visible range, thus exceeding the normal human sensing. In this paper we investigate algorithms that improve face recognition by extracting the 'best bands' according to various criteria such as decorrelation and statistical independence. The work expands on previous band extraction results and has the distinct advantage of being one of the first that combines spatial information (i.e. face characteristics) with spectral information.

AB - Among various biometrics measures used in human identification, face recognition, has the distinct advantage of not requiring the subjects collaboration. Hyperspectral data constitute a natural choice for expanding face recognition image fusion, especially since it may provide information beyond the normal visible range, thus exceeding the normal human sensing. In this paper we investigate algorithms that improve face recognition by extracting the 'best bands' according to various criteria such as decorrelation and statistical independence. The work expands on previous band extraction results and has the distinct advantage of being one of the first that combines spatial information (i.e. face characteristics) with spectral information.

KW - Face recognition

KW - Feature extraction

KW - Hyperspectral data

UR - http://www.scopus.com/inward/record.url?scp=69949168414&partnerID=8YFLogxK

U2 - 10.1117/12.817025

DO - 10.1117/12.817025

M3 - Conference contribution

AN - SCOPUS:69949168414

SN - 9780819476005

VL - 7334

BT - Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XV

Y2 - 13 April 2009 through 16 April 2009

ER -

Investigating face recognition from hyperspectral data: Impact of band extraction

Abstract

Other

Keywords

Access to Document

Other files and links

Fingerprint

Cite this