A pyroelectric infrared biometric system for real-time walker recognition by use of a maximum likelihood principal components estimation (MLPCE) method

Jian Shuen Fang; Qi Hao; David J. Brady; Bob D. Guenther; Ken Y. Hsu

doi:10.1364/OE.15.003271

A pyroelectric infrared biometric system for real-time walker recognition by use of a maximum likelihood principal components estimation (MLPCE) method

Jian Shuen Fang, Qi Hao, David J. Brady, Bob D. Guenther, Ken Y. Hsu

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

37 Scopus citations

Abstract

This paper presents a novel biometric system for real-time walker recognition using a pyroelectric infrared sensor, a Fresnel lens array and signal processing based on the linear regression of sensor signal spectra. In the model training stage, the maximum likelihood principal components estimation (MLPCE) method is utilized to obtain the regression vector for each registered human subject. Receiver operating characteristic (ROC) curves are also investigated to select a suitable threshold for maximizing subject recognition rate. The experimental results demonstrate the effectiveness of the proposed pyroelectric sensor system in recognizing registered subjects and rejecting unknown subjects.

Original language	English (US)
Pages (from-to)	3271-3284
Number of pages	14
Journal	Optics Express
Volume	15
Issue number	6
DOIs	https://doi.org/10.1364/OE.15.003271
State	Published - Mar 19 2007
Externally published	Yes

ASJC Scopus subject areas

Atomic and Molecular Physics, and Optics

Access to Document

10.1364/OE.15.003271

Cite this

@article{97a0c5620bca4ae18446663d39eb7e5e,

title = "A pyroelectric infrared biometric system for real-time walker recognition by use of a maximum likelihood principal components estimation (MLPCE) method",

abstract = "This paper presents a novel biometric system for real-time walker recognition using a pyroelectric infrared sensor, a Fresnel lens array and signal processing based on the linear regression of sensor signal spectra. In the model training stage, the maximum likelihood principal components estimation (MLPCE) method is utilized to obtain the regression vector for each registered human subject. Receiver operating characteristic (ROC) curves are also investigated to select a suitable threshold for maximizing subject recognition rate. The experimental results demonstrate the effectiveness of the proposed pyroelectric sensor system in recognizing registered subjects and rejecting unknown subjects.",

author = "Fang, {Jian Shuen} and Qi Hao and Brady, {David J.} and Guenther, {Bob D.} and Hsu, {Ken Y.}",

year = "2007",

month = mar,

day = "19",

doi = "10.1364/OE.15.003271",

language = "English (US)",

volume = "15",

pages = "3271--3284",

journal = "Optics Express",

issn = "1094-4087",

publisher = "The Optical Society",

number = "6",

}

TY - JOUR

T1 - A pyroelectric infrared biometric system for real-time walker recognition by use of a maximum likelihood principal components estimation (MLPCE) method

AU - Fang, Jian Shuen

AU - Hao, Qi

AU - Brady, David J.

AU - Guenther, Bob D.

AU - Hsu, Ken Y.

PY - 2007/3/19

Y1 - 2007/3/19

N2 - This paper presents a novel biometric system for real-time walker recognition using a pyroelectric infrared sensor, a Fresnel lens array and signal processing based on the linear regression of sensor signal spectra. In the model training stage, the maximum likelihood principal components estimation (MLPCE) method is utilized to obtain the regression vector for each registered human subject. Receiver operating characteristic (ROC) curves are also investigated to select a suitable threshold for maximizing subject recognition rate. The experimental results demonstrate the effectiveness of the proposed pyroelectric sensor system in recognizing registered subjects and rejecting unknown subjects.

AB - This paper presents a novel biometric system for real-time walker recognition using a pyroelectric infrared sensor, a Fresnel lens array and signal processing based on the linear regression of sensor signal spectra. In the model training stage, the maximum likelihood principal components estimation (MLPCE) method is utilized to obtain the regression vector for each registered human subject. Receiver operating characteristic (ROC) curves are also investigated to select a suitable threshold for maximizing subject recognition rate. The experimental results demonstrate the effectiveness of the proposed pyroelectric sensor system in recognizing registered subjects and rejecting unknown subjects.

UR - http://www.scopus.com/inward/record.url?scp=33947380126&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33947380126&partnerID=8YFLogxK

U2 - 10.1364/OE.15.003271

DO - 10.1364/OE.15.003271

M3 - Article

AN - SCOPUS:33947380126

SN - 1094-4087

VL - 15

SP - 3271

EP - 3284

JO - Optics Express

JF - Optics Express

IS - 6

ER -

A pyroelectric infrared biometric system for real-time walker recognition by use of a maximum likelihood principal components estimation (MLPCE) method

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this