Heartbeat Signal from Facial Video for Biometric Recognition

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

11 Citationer (Scopus)
1291 Downloads (Pure)

Resumé

Different biometric traits such as face appearance and heartbeat signal from Electrocardiogram (ECG)/Phonocardiogram (PCG) are widely used in the human identity recognition. Recent advances in facial video based measurement of cardio-physiological parameters such as heartbeat rate, respiratory rate, and blood volume pressure provide the possibility of extracting heartbeat signal from facial video instead of using obtrusive ECG or PCG sensors in the body. This paper proposes the Heartbeat Signal from Facial Video (HSFV) as a new biometric trait for human identity recognition, for the first time to the best of our knowledge. Feature extraction from the HSFV is accomplished by employing Radon transform on a waterfall model of the replicated HSFV. The pairwise Minkowski distances are obtained from the Radon image as the features. The authentication is accomplished by a decision tree based supervised approach. The potential of the proposed HSFV biometric for human identification is demonstrated on a public database.
OriginalsprogEngelsk
TitelImage Analysis : 19th Scandinavian Conference, SCIA 2015, Copenhagen, Denmark, June 15-17, 2015. Proceedings
Antal sider12
ForlagSpringer
Publikationsdato2015
Sider165-174
ISBN (Trykt)978-3-319-19664-0
ISBN (Elektronisk)978-3-319-19665-7
DOI
StatusUdgivet - 2015
BegivenhedScandinavian Conference on Image Analysis - Copenhagen, Danmark
Varighed: 15 jun. 201517 jun. 2015
Konferencens nummer: 19

Konference

KonferenceScandinavian Conference on Image Analysis
Nummer19
LandDanmark
ByCopenhagen
Periode15/06/201517/06/2015
NavnLecture Notes in Computer Science
Vol/bind9127
ISSN0302-9743

Fingerprint

Biometrics
Radon
Electrocardiography
Decision trees
Authentication
Feature extraction
Blood
Sensors

Citer dette

Haque, M. A., Nasrollahi, K., & Moeslund, T. B. (2015). Heartbeat Signal from Facial Video for Biometric Recognition. I Image Analysis: 19th Scandinavian Conference, SCIA 2015, Copenhagen, Denmark, June 15-17, 2015. Proceedings (s. 165-174). Springer. Lecture Notes in Computer Science, Bind. 9127 https://doi.org/10.1007/978-3-319-19665-7_14
Haque, Mohammad Ahsanul ; Nasrollahi, Kamal ; Moeslund, Thomas B. / Heartbeat Signal from Facial Video for Biometric Recognition. Image Analysis: 19th Scandinavian Conference, SCIA 2015, Copenhagen, Denmark, June 15-17, 2015. Proceedings. Springer, 2015. s. 165-174 (Lecture Notes in Computer Science, Bind 9127).
@inproceedings{a2bb5d70f43c4b37b9bf6331556a9499,
title = "Heartbeat Signal from Facial Video for Biometric Recognition",
abstract = "Different biometric traits such as face appearance and heartbeat signal from Electrocardiogram (ECG)/Phonocardiogram (PCG) are widely used in the human identity recognition. Recent advances in facial video based measurement of cardio-physiological parameters such as heartbeat rate, respiratory rate, and blood volume pressure provide the possibility of extracting heartbeat signal from facial video instead of using obtrusive ECG or PCG sensors in the body. This paper proposes the Heartbeat Signal from Facial Video (HSFV) as a new biometric trait for human identity recognition, for the first time to the best of our knowledge. Feature extraction from the HSFV is accomplished by employing Radon transform on a waterfall model of the replicated HSFV. The pairwise Minkowski distances are obtained from the Radon image as the features. The authentication is accomplished by a decision tree based supervised approach. The potential of the proposed HSFV biometric for human identification is demonstrated on a public database.",
keywords = "biometric, identification, Radon transform, heartbeat, facial video",
author = "Haque, {Mohammad Ahsanul} and Kamal Nasrollahi and Moeslund, {Thomas B.}",
year = "2015",
doi = "10.1007/978-3-319-19665-7_14",
language = "English",
isbn = "978-3-319-19664-0",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
pages = "165--174",
booktitle = "Image Analysis",
address = "Germany",

}

Haque, MA, Nasrollahi, K & Moeslund, TB 2015, Heartbeat Signal from Facial Video for Biometric Recognition. i Image Analysis: 19th Scandinavian Conference, SCIA 2015, Copenhagen, Denmark, June 15-17, 2015. Proceedings. Springer, Lecture Notes in Computer Science, bind 9127, s. 165-174, Scandinavian Conference on Image Analysis, Copenhagen, Danmark, 15/06/2015. https://doi.org/10.1007/978-3-319-19665-7_14

Heartbeat Signal from Facial Video for Biometric Recognition. / Haque, Mohammad Ahsanul; Nasrollahi, Kamal; Moeslund, Thomas B.

Image Analysis: 19th Scandinavian Conference, SCIA 2015, Copenhagen, Denmark, June 15-17, 2015. Proceedings. Springer, 2015. s. 165-174 (Lecture Notes in Computer Science, Bind 9127).

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

TY - GEN

T1 - Heartbeat Signal from Facial Video for Biometric Recognition

AU - Haque, Mohammad Ahsanul

AU - Nasrollahi, Kamal

AU - Moeslund, Thomas B.

PY - 2015

Y1 - 2015

N2 - Different biometric traits such as face appearance and heartbeat signal from Electrocardiogram (ECG)/Phonocardiogram (PCG) are widely used in the human identity recognition. Recent advances in facial video based measurement of cardio-physiological parameters such as heartbeat rate, respiratory rate, and blood volume pressure provide the possibility of extracting heartbeat signal from facial video instead of using obtrusive ECG or PCG sensors in the body. This paper proposes the Heartbeat Signal from Facial Video (HSFV) as a new biometric trait for human identity recognition, for the first time to the best of our knowledge. Feature extraction from the HSFV is accomplished by employing Radon transform on a waterfall model of the replicated HSFV. The pairwise Minkowski distances are obtained from the Radon image as the features. The authentication is accomplished by a decision tree based supervised approach. The potential of the proposed HSFV biometric for human identification is demonstrated on a public database.

AB - Different biometric traits such as face appearance and heartbeat signal from Electrocardiogram (ECG)/Phonocardiogram (PCG) are widely used in the human identity recognition. Recent advances in facial video based measurement of cardio-physiological parameters such as heartbeat rate, respiratory rate, and blood volume pressure provide the possibility of extracting heartbeat signal from facial video instead of using obtrusive ECG or PCG sensors in the body. This paper proposes the Heartbeat Signal from Facial Video (HSFV) as a new biometric trait for human identity recognition, for the first time to the best of our knowledge. Feature extraction from the HSFV is accomplished by employing Radon transform on a waterfall model of the replicated HSFV. The pairwise Minkowski distances are obtained from the Radon image as the features. The authentication is accomplished by a decision tree based supervised approach. The potential of the proposed HSFV biometric for human identification is demonstrated on a public database.

KW - biometric

KW - identification

KW - Radon transform

KW - heartbeat

KW - facial video

U2 - 10.1007/978-3-319-19665-7_14

DO - 10.1007/978-3-319-19665-7_14

M3 - Article in proceeding

SN - 978-3-319-19664-0

T3 - Lecture Notes in Computer Science

SP - 165

EP - 174

BT - Image Analysis

PB - Springer

ER -

Haque MA, Nasrollahi K, Moeslund TB. Heartbeat Signal from Facial Video for Biometric Recognition. I Image Analysis: 19th Scandinavian Conference, SCIA 2015, Copenhagen, Denmark, June 15-17, 2015. Proceedings. Springer. 2015. s. 165-174. (Lecture Notes in Computer Science, Bind 9127). https://doi.org/10.1007/978-3-319-19665-7_14