De-Duplication Using Automated Face Recognition: A Mathematical Model and All Babies Are Equally Cute

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

35 Downloads (Pure)

Abstract

De-duplication is defined as the technique to eliminate or link duplicate copies of repeating data. We consider a specific de-duplication application where a subject applies for a new passport and we want to check if he possesses a passport already under another name. To determine this, a facial photograph of the subject is compared to all photographs of the national database of passports. We investigate if state of the art facial recognition is up to this task and find that for a large database about 2 out of 3 duplicates can be found while few or no false duplicates are reported. This means that de-duplication using automated face recognition is feasible in practice. We also present a mathematical model to predict the performance of de-duplication and find that the probability that k false duplicates are returned can be described well by a Poisson distribution using a varying, subject specific false match rate. We present experimental results using a large database of actual passport photographs consisting of 224 000 images of about 100 000 subjects and find that the results are predicted well by our model.

Original languageEnglish
Title of host publication2017 International Conference of the Biometrics Special Interest Group, BIOSIG 2017
PublisherGesellschaft für Informatik
ISBN (Electronic)978-3-88579-664-0
ISBN (Print)978-1-5386-0396-3
DOIs
Publication statusPublished - 28 Sep 2017
Event16th International Conference of the Biometrics Special Interest Group 2017 - Darmstadt, Germany
Duration: 20 Sep 201722 Sep 2017
Conference number: 16
http://fg-biosig.gi.de/archiv/biosig-2017.html

Conference

Conference16th International Conference of the Biometrics Special Interest Group 2017
Abbreviated titleBIOSIG 2017
CountryGermany
CityDarmstadt
Period20/09/1722/09/17
Internet address

Fingerprint

Face recognition
Mathematical models
Poisson distribution

Cite this

Spreeuwers, L. (2017). De-Duplication Using Automated Face Recognition: A Mathematical Model and All Babies Are Equally Cute. In 2017 International Conference of the Biometrics Special Interest Group, BIOSIG 2017 [8053500] Gesellschaft für Informatik. https://doi.org/10.23919/BIOSIG.2017.8053500
Spreeuwers, Luuk. / De-Duplication Using Automated Face Recognition : A Mathematical Model and All Babies Are Equally Cute. 2017 International Conference of the Biometrics Special Interest Group, BIOSIG 2017. Gesellschaft für Informatik, 2017.
@inproceedings{497b3b79b55e4df18b26203e4a604f9b,
title = "De-Duplication Using Automated Face Recognition: A Mathematical Model and All Babies Are Equally Cute",
abstract = "De-duplication is defined as the technique to eliminate or link duplicate copies of repeating data. We consider a specific de-duplication application where a subject applies for a new passport and we want to check if he possesses a passport already under another name. To determine this, a facial photograph of the subject is compared to all photographs of the national database of passports. We investigate if state of the art facial recognition is up to this task and find that for a large database about 2 out of 3 duplicates can be found while few or no false duplicates are reported. This means that de-duplication using automated face recognition is feasible in practice. We also present a mathematical model to predict the performance of de-duplication and find that the probability that k false duplicates are returned can be described well by a Poisson distribution using a varying, subject specific false match rate. We present experimental results using a large database of actual passport photographs consisting of 224 000 images of about 100 000 subjects and find that the results are predicted well by our model.",
author = "Luuk Spreeuwers",
year = "2017",
month = "9",
day = "28",
doi = "10.23919/BIOSIG.2017.8053500",
language = "English",
isbn = "978-1-5386-0396-3",
booktitle = "2017 International Conference of the Biometrics Special Interest Group, BIOSIG 2017",
publisher = "Gesellschaft f{\"u}r Informatik",
address = "Germany",

}

Spreeuwers, L 2017, De-Duplication Using Automated Face Recognition: A Mathematical Model and All Babies Are Equally Cute. in 2017 International Conference of the Biometrics Special Interest Group, BIOSIG 2017., 8053500, Gesellschaft für Informatik, 16th International Conference of the Biometrics Special Interest Group 2017, Darmstadt, Germany, 20/09/17. https://doi.org/10.23919/BIOSIG.2017.8053500

De-Duplication Using Automated Face Recognition : A Mathematical Model and All Babies Are Equally Cute. / Spreeuwers, Luuk.

2017 International Conference of the Biometrics Special Interest Group, BIOSIG 2017. Gesellschaft für Informatik, 2017. 8053500.

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - De-Duplication Using Automated Face Recognition

T2 - A Mathematical Model and All Babies Are Equally Cute

AU - Spreeuwers, Luuk

PY - 2017/9/28

Y1 - 2017/9/28

N2 - De-duplication is defined as the technique to eliminate or link duplicate copies of repeating data. We consider a specific de-duplication application where a subject applies for a new passport and we want to check if he possesses a passport already under another name. To determine this, a facial photograph of the subject is compared to all photographs of the national database of passports. We investigate if state of the art facial recognition is up to this task and find that for a large database about 2 out of 3 duplicates can be found while few or no false duplicates are reported. This means that de-duplication using automated face recognition is feasible in practice. We also present a mathematical model to predict the performance of de-duplication and find that the probability that k false duplicates are returned can be described well by a Poisson distribution using a varying, subject specific false match rate. We present experimental results using a large database of actual passport photographs consisting of 224 000 images of about 100 000 subjects and find that the results are predicted well by our model.

AB - De-duplication is defined as the technique to eliminate or link duplicate copies of repeating data. We consider a specific de-duplication application where a subject applies for a new passport and we want to check if he possesses a passport already under another name. To determine this, a facial photograph of the subject is compared to all photographs of the national database of passports. We investigate if state of the art facial recognition is up to this task and find that for a large database about 2 out of 3 duplicates can be found while few or no false duplicates are reported. This means that de-duplication using automated face recognition is feasible in practice. We also present a mathematical model to predict the performance of de-duplication and find that the probability that k false duplicates are returned can be described well by a Poisson distribution using a varying, subject specific false match rate. We present experimental results using a large database of actual passport photographs consisting of 224 000 images of about 100 000 subjects and find that the results are predicted well by our model.

UR - http://www.scopus.com/inward/record.url?scp=85034615132&partnerID=8YFLogxK

U2 - 10.23919/BIOSIG.2017.8053500

DO - 10.23919/BIOSIG.2017.8053500

M3 - Conference contribution

SN - 978-1-5386-0396-3

BT - 2017 International Conference of the Biometrics Special Interest Group, BIOSIG 2017

PB - Gesellschaft für Informatik

ER -

Spreeuwers L. De-Duplication Using Automated Face Recognition: A Mathematical Model and All Babies Are Equally Cute. In 2017 International Conference of the Biometrics Special Interest Group, BIOSIG 2017. Gesellschaft für Informatik. 2017. 8053500 https://doi.org/10.23919/BIOSIG.2017.8053500