An authentication method by high spectral resolution palm datacube

Yuta Sato, Fumitsugu Akazawa, Daigo Muramatsu, Takashi Matsumoto, Atsushi Nakamura, Takayuki Sota

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

1 Citation (Scopus)

Abstract

A biometric authentication method is proposed based on hyper spectral image data derived from the palm of the hand. The data are acquired using a recently developed device that captures reflectance across the 396.37-990.64 nm range with a spectral resolution of 0.93 nm. The acquired image data represent the distributions of various biological substances. First, the proposed method computes the spatial correlations between the test data and a set of stored template data for each wavelength of the spectrally resolved image. Next, the algorithm computes a score by integrating the spatial correlations for each wavelength. This method incorporates the well-known vein structure in the NIR range and other rather intricate structures located in the shallower parts of hands. In the evaluation, 1500 data were acquired from 30 subjects and the equal error rate was 0.611%.

Original languageEnglish
Title of host publicationProceedings - 2013 International Conference on Biometrics and Kansei Engineering, ICBAKE 2013
Pages239-244
Number of pages6
DOIs
Publication statusPublished - 2013
Event2013 International Conference on Biometrics and Kansei Engineering, ICBAKE 2013 - Tokyo, Japan
Duration: 2013 Jul 52013 Jul 7

Other

Other2013 International Conference on Biometrics and Kansei Engineering, ICBAKE 2013
CountryJapan
CityTokyo
Period13/7/513/7/7

Fingerprint

Biometric Identification
Hand
Veins
Equipment and Supplies
Datasets

Keywords

  • Biometric authentication
  • Hyperspectral datacube
  • Spectrally resolved images

ASJC Scopus subject areas

  • Biotechnology

Cite this

Sato, Y., Akazawa, F., Muramatsu, D., Matsumoto, T., Nakamura, A., & Sota, T. (2013). An authentication method by high spectral resolution palm datacube. In Proceedings - 2013 International Conference on Biometrics and Kansei Engineering, ICBAKE 2013 (pp. 239-244). [6603509] https://doi.org/10.1109/ICBAKE.2013.47

An authentication method by high spectral resolution palm datacube. / Sato, Yuta; Akazawa, Fumitsugu; Muramatsu, Daigo; Matsumoto, Takashi; Nakamura, Atsushi; Sota, Takayuki.

Proceedings - 2013 International Conference on Biometrics and Kansei Engineering, ICBAKE 2013. 2013. p. 239-244 6603509.

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

Sato, Y, Akazawa, F, Muramatsu, D, Matsumoto, T, Nakamura, A & Sota, T 2013, An authentication method by high spectral resolution palm datacube. in Proceedings - 2013 International Conference on Biometrics and Kansei Engineering, ICBAKE 2013., 6603509, pp. 239-244, 2013 International Conference on Biometrics and Kansei Engineering, ICBAKE 2013, Tokyo, Japan, 13/7/5. https://doi.org/10.1109/ICBAKE.2013.47
Sato Y, Akazawa F, Muramatsu D, Matsumoto T, Nakamura A, Sota T. An authentication method by high spectral resolution palm datacube. In Proceedings - 2013 International Conference on Biometrics and Kansei Engineering, ICBAKE 2013. 2013. p. 239-244. 6603509 https://doi.org/10.1109/ICBAKE.2013.47
Sato, Yuta ; Akazawa, Fumitsugu ; Muramatsu, Daigo ; Matsumoto, Takashi ; Nakamura, Atsushi ; Sota, Takayuki. / An authentication method by high spectral resolution palm datacube. Proceedings - 2013 International Conference on Biometrics and Kansei Engineering, ICBAKE 2013. 2013. pp. 239-244
@inproceedings{641a4caff8614ee8bb77618ca771d5fd,
title = "An authentication method by high spectral resolution palm datacube",
abstract = "A biometric authentication method is proposed based on hyper spectral image data derived from the palm of the hand. The data are acquired using a recently developed device that captures reflectance across the 396.37-990.64 nm range with a spectral resolution of 0.93 nm. The acquired image data represent the distributions of various biological substances. First, the proposed method computes the spatial correlations between the test data and a set of stored template data for each wavelength of the spectrally resolved image. Next, the algorithm computes a score by integrating the spatial correlations for each wavelength. This method incorporates the well-known vein structure in the NIR range and other rather intricate structures located in the shallower parts of hands. In the evaluation, 1500 data were acquired from 30 subjects and the equal error rate was 0.611{\%}.",
keywords = "Biometric authentication, Hyperspectral datacube, Spectrally resolved images",
author = "Yuta Sato and Fumitsugu Akazawa and Daigo Muramatsu and Takashi Matsumoto and Atsushi Nakamura and Takayuki Sota",
year = "2013",
doi = "10.1109/ICBAKE.2013.47",
language = "English",
isbn = "9780769550190",
pages = "239--244",
booktitle = "Proceedings - 2013 International Conference on Biometrics and Kansei Engineering, ICBAKE 2013",

}

TY - GEN

T1 - An authentication method by high spectral resolution palm datacube

AU - Sato, Yuta

AU - Akazawa, Fumitsugu

AU - Muramatsu, Daigo

AU - Matsumoto, Takashi

AU - Nakamura, Atsushi

AU - Sota, Takayuki

PY - 2013

Y1 - 2013

N2 - A biometric authentication method is proposed based on hyper spectral image data derived from the palm of the hand. The data are acquired using a recently developed device that captures reflectance across the 396.37-990.64 nm range with a spectral resolution of 0.93 nm. The acquired image data represent the distributions of various biological substances. First, the proposed method computes the spatial correlations between the test data and a set of stored template data for each wavelength of the spectrally resolved image. Next, the algorithm computes a score by integrating the spatial correlations for each wavelength. This method incorporates the well-known vein structure in the NIR range and other rather intricate structures located in the shallower parts of hands. In the evaluation, 1500 data were acquired from 30 subjects and the equal error rate was 0.611%.

AB - A biometric authentication method is proposed based on hyper spectral image data derived from the palm of the hand. The data are acquired using a recently developed device that captures reflectance across the 396.37-990.64 nm range with a spectral resolution of 0.93 nm. The acquired image data represent the distributions of various biological substances. First, the proposed method computes the spatial correlations between the test data and a set of stored template data for each wavelength of the spectrally resolved image. Next, the algorithm computes a score by integrating the spatial correlations for each wavelength. This method incorporates the well-known vein structure in the NIR range and other rather intricate structures located in the shallower parts of hands. In the evaluation, 1500 data were acquired from 30 subjects and the equal error rate was 0.611%.

KW - Biometric authentication

KW - Hyperspectral datacube

KW - Spectrally resolved images

UR - http://www.scopus.com/inward/record.url?scp=84885393247&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84885393247&partnerID=8YFLogxK

U2 - 10.1109/ICBAKE.2013.47

DO - 10.1109/ICBAKE.2013.47

M3 - Conference contribution

AN - SCOPUS:84885393247

SN - 9780769550190

SP - 239

EP - 244

BT - Proceedings - 2013 International Conference on Biometrics and Kansei Engineering, ICBAKE 2013

ER -