Toward hyperspectral face recognition

Research output: Chapter in Book/Report/Conference proceedingConference contribution

22 Citations (Scopus)

Abstract

Face recognition continues to meet significant challenges in reaching accurate results and still remains one of the activities where humans outperform technology. An attractive approach in improving face identification is provided by the fusion of multiple imaging sources such as visible and infrared images. Hyperspectral data, i.e. images collected over hundreds of narrow contiguous light spectrum intervals 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 the efficiency of hyperspectral face recognition through an in house experiment that collected data in over 120 bands within the visible and near infrared range. The imagery was produced using an off the shelf sensor in both indoors and outdoors with the subjects being photographed from various angles. Further processing included spectra collection and feature extraction. Human matching performance based on spectral properties is discussed.

Original languageEnglish
Title of host publicationProceedings of SPIE-IS and T Electronic Imaging -Image Processing
Subtitle of host publicationAlgorithms and Systems VI
DOIs
StatePublished - 15 May 2008
EventImage Processing: Algorithms and Systems VI - San Jose, CA, United States
Duration: 28 Jan 200829 Jan 2008

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume6812
ISSN (Print)0277-786X

Other

OtherImage Processing: Algorithms and Systems VI
CountryUnited States
CitySan Jose, CA
Period28/01/0829/01/08

Fingerprint

Face recognition
fusion
Infrared radiation
Image fusion
shelves
pattern recognition
imagery
Feature extraction
intervals
Imaging techniques
sensors
Sensors
Processing
Experiments

Keywords

  • Face recognition
  • Hyperspectral imagery
  • Spectral matching

Cite this

Robila, S. A. (2008). Toward hyperspectral face recognition. In Proceedings of SPIE-IS and T Electronic Imaging -Image Processing: Algorithms and Systems VI [68120X] (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 6812). https://doi.org/10.1117/12.765268
Robila, Stefan A. / Toward hyperspectral face recognition. Proceedings of SPIE-IS and T Electronic Imaging -Image Processing: Algorithms and Systems VI. 2008. (Proceedings of SPIE - The International Society for Optical Engineering).
@inproceedings{2386e6e7697e4baa8ad8b8cf5c449e1a,
title = "Toward hyperspectral face recognition",
abstract = "Face recognition continues to meet significant challenges in reaching accurate results and still remains one of the activities where humans outperform technology. An attractive approach in improving face identification is provided by the fusion of multiple imaging sources such as visible and infrared images. Hyperspectral data, i.e. images collected over hundreds of narrow contiguous light spectrum intervals 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 the efficiency of hyperspectral face recognition through an in house experiment that collected data in over 120 bands within the visible and near infrared range. The imagery was produced using an off the shelf sensor in both indoors and outdoors with the subjects being photographed from various angles. Further processing included spectra collection and feature extraction. Human matching performance based on spectral properties is discussed.",
keywords = "Face recognition, Hyperspectral imagery, Spectral matching",
author = "Robila, {Stefan A.}",
year = "2008",
month = "5",
day = "15",
doi = "10.1117/12.765268",
language = "English",
isbn = "9780819469847",
series = "Proceedings of SPIE - The International Society for Optical Engineering",
booktitle = "Proceedings of SPIE-IS and T Electronic Imaging -Image Processing",

}

Robila, SA 2008, Toward hyperspectral face recognition. in Proceedings of SPIE-IS and T Electronic Imaging -Image Processing: Algorithms and Systems VI., 68120X, Proceedings of SPIE - The International Society for Optical Engineering, vol. 6812, Image Processing: Algorithms and Systems VI, San Jose, CA, United States, 28/01/08. https://doi.org/10.1117/12.765268

Toward hyperspectral face recognition. / Robila, Stefan A.

Proceedings of SPIE-IS and T Electronic Imaging -Image Processing: Algorithms and Systems VI. 2008. 68120X (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 6812).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Toward hyperspectral face recognition

AU - Robila, Stefan A.

PY - 2008/5/15

Y1 - 2008/5/15

N2 - Face recognition continues to meet significant challenges in reaching accurate results and still remains one of the activities where humans outperform technology. An attractive approach in improving face identification is provided by the fusion of multiple imaging sources such as visible and infrared images. Hyperspectral data, i.e. images collected over hundreds of narrow contiguous light spectrum intervals 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 the efficiency of hyperspectral face recognition through an in house experiment that collected data in over 120 bands within the visible and near infrared range. The imagery was produced using an off the shelf sensor in both indoors and outdoors with the subjects being photographed from various angles. Further processing included spectra collection and feature extraction. Human matching performance based on spectral properties is discussed.

AB - Face recognition continues to meet significant challenges in reaching accurate results and still remains one of the activities where humans outperform technology. An attractive approach in improving face identification is provided by the fusion of multiple imaging sources such as visible and infrared images. Hyperspectral data, i.e. images collected over hundreds of narrow contiguous light spectrum intervals 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 the efficiency of hyperspectral face recognition through an in house experiment that collected data in over 120 bands within the visible and near infrared range. The imagery was produced using an off the shelf sensor in both indoors and outdoors with the subjects being photographed from various angles. Further processing included spectra collection and feature extraction. Human matching performance based on spectral properties is discussed.

KW - Face recognition

KW - Hyperspectral imagery

KW - Spectral matching

UR - http://www.scopus.com/inward/record.url?scp=43249109878&partnerID=8YFLogxK

U2 - 10.1117/12.765268

DO - 10.1117/12.765268

M3 - Conference contribution

AN - SCOPUS:43249109878

SN - 9780819469847

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

BT - Proceedings of SPIE-IS and T Electronic Imaging -Image Processing

ER -

Robila SA. Toward hyperspectral face recognition. In Proceedings of SPIE-IS and T Electronic Imaging -Image Processing: Algorithms and Systems VI. 2008. 68120X. (Proceedings of SPIE - The International Society for Optical Engineering). https://doi.org/10.1117/12.765268