Mind the Gap: A practical framework for classifiers in a forensic context

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

Abstract

In this paper, we present a practical framework that addresses six, mostly forensic, aspects that can be considered during the design and evaluation of biometric classifiers for the purpose of forensic evidence evaluation. Forensic evidence evaluation is a central activity in forensic case work, it includes the assessment of strength of evidence of trace and reference specimens and its outcome may be used in a court of law. The addressed aspects consider the modality and features, the biometric score and its forensic use, and choice and evaluation of several performance characteristics and metrics. The aim of the framework is to make the design and evaluation choices more transparent. We also present two applications of the framework pertaining to forensic face recognition. Using the framework, we can demonstrate large and explainable variations in discriminating power between subjects.

Original languageEnglish
Title of host publication2018 IEEE 9th International Conference on Biometrics Theory, Applications and Systems, BTAS 2018
Place of PublicationPiscataway, NJ
PublisherIEEE
ISBN (Electronic)978-1-5386-7179-5, 978-1-5386-7180-1
ISBN (Print)978-1-5386-7181-8
DOIs
Publication statusPublished - 25 Apr 2019
Event2018 IEEE 9th International Conference on Biometrics Theory, Applications and Systems, BTAS 2018 - Torrance Marriott Redondo Beach, Los Angeles, United States
Duration: 22 Oct 201825 Oct 2018
Conference number: 9

Publication series

NameIEEE nternational Conference on Biometrics Theory, Applications and Systems (BTAS)
PublisherIEEE
Volume2018
ISSN (Print)2474-9680
ISSN (Electronic)2474-9699

Conference

Conference2018 IEEE 9th International Conference on Biometrics Theory, Applications and Systems, BTAS 2018
Abbreviated titleBTAS
CountryUnited States
CityLos Angeles
Period22/10/1825/10/18

Fingerprint

Biometrics
Classifiers
Classifier
Face recognition
Evaluation
Face Recognition
Modality
Context
Framework
Trace
Metric
Demonstrate
Evidence

Cite this

Zeinstra, C., Meuwly, D., Veldhuis, R., & Spreeuwers, L. (2019). Mind the Gap: A practical framework for classifiers in a forensic context. In 2018 IEEE 9th International Conference on Biometrics Theory, Applications and Systems, BTAS 2018 [8698583] (IEEE nternational Conference on Biometrics Theory, Applications and Systems (BTAS); Vol. 2018). Piscataway, NJ: IEEE. https://doi.org/10.1109/BTAS.2018.8698583
Zeinstra, Chris ; Meuwly, Didier ; Veldhuis, Raymond ; Spreeuwers, Luuk. / Mind the Gap : A practical framework for classifiers in a forensic context. 2018 IEEE 9th International Conference on Biometrics Theory, Applications and Systems, BTAS 2018. Piscataway, NJ : IEEE, 2019. (IEEE nternational Conference on Biometrics Theory, Applications and Systems (BTAS)).
@inproceedings{6f20e01a040a4c59b609b50477bc9eb1,
title = "Mind the Gap: A practical framework for classifiers in a forensic context",
abstract = "In this paper, we present a practical framework that addresses six, mostly forensic, aspects that can be considered during the design and evaluation of biometric classifiers for the purpose of forensic evidence evaluation. Forensic evidence evaluation is a central activity in forensic case work, it includes the assessment of strength of evidence of trace and reference specimens and its outcome may be used in a court of law. The addressed aspects consider the modality and features, the biometric score and its forensic use, and choice and evaluation of several performance characteristics and metrics. The aim of the framework is to make the design and evaluation choices more transparent. We also present two applications of the framework pertaining to forensic face recognition. Using the framework, we can demonstrate large and explainable variations in discriminating power between subjects.",
author = "Chris Zeinstra and Didier Meuwly and Raymond Veldhuis and Luuk Spreeuwers",
year = "2019",
month = "4",
day = "25",
doi = "10.1109/BTAS.2018.8698583",
language = "English",
isbn = "978-1-5386-7181-8",
series = "IEEE nternational Conference on Biometrics Theory, Applications and Systems (BTAS)",
publisher = "IEEE",
booktitle = "2018 IEEE 9th International Conference on Biometrics Theory, Applications and Systems, BTAS 2018",
address = "United States",

}

Zeinstra, C, Meuwly, D, Veldhuis, R & Spreeuwers, L 2019, Mind the Gap: A practical framework for classifiers in a forensic context. in 2018 IEEE 9th International Conference on Biometrics Theory, Applications and Systems, BTAS 2018., 8698583, IEEE nternational Conference on Biometrics Theory, Applications and Systems (BTAS), vol. 2018, IEEE, Piscataway, NJ, 2018 IEEE 9th International Conference on Biometrics Theory, Applications and Systems, BTAS 2018, Los Angeles, United States, 22/10/18. https://doi.org/10.1109/BTAS.2018.8698583

Mind the Gap : A practical framework for classifiers in a forensic context. / Zeinstra, Chris; Meuwly, Didier; Veldhuis, Raymond; Spreeuwers, Luuk.

2018 IEEE 9th International Conference on Biometrics Theory, Applications and Systems, BTAS 2018. Piscataway, NJ : IEEE, 2019. 8698583 (IEEE nternational Conference on Biometrics Theory, Applications and Systems (BTAS); Vol. 2018).

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

TY - GEN

T1 - Mind the Gap

T2 - A practical framework for classifiers in a forensic context

AU - Zeinstra, Chris

AU - Meuwly, Didier

AU - Veldhuis, Raymond

AU - Spreeuwers, Luuk

PY - 2019/4/25

Y1 - 2019/4/25

N2 - In this paper, we present a practical framework that addresses six, mostly forensic, aspects that can be considered during the design and evaluation of biometric classifiers for the purpose of forensic evidence evaluation. Forensic evidence evaluation is a central activity in forensic case work, it includes the assessment of strength of evidence of trace and reference specimens and its outcome may be used in a court of law. The addressed aspects consider the modality and features, the biometric score and its forensic use, and choice and evaluation of several performance characteristics and metrics. The aim of the framework is to make the design and evaluation choices more transparent. We also present two applications of the framework pertaining to forensic face recognition. Using the framework, we can demonstrate large and explainable variations in discriminating power between subjects.

AB - In this paper, we present a practical framework that addresses six, mostly forensic, aspects that can be considered during the design and evaluation of biometric classifiers for the purpose of forensic evidence evaluation. Forensic evidence evaluation is a central activity in forensic case work, it includes the assessment of strength of evidence of trace and reference specimens and its outcome may be used in a court of law. The addressed aspects consider the modality and features, the biometric score and its forensic use, and choice and evaluation of several performance characteristics and metrics. The aim of the framework is to make the design and evaluation choices more transparent. We also present two applications of the framework pertaining to forensic face recognition. Using the framework, we can demonstrate large and explainable variations in discriminating power between subjects.

U2 - 10.1109/BTAS.2018.8698583

DO - 10.1109/BTAS.2018.8698583

M3 - Conference contribution

SN - 978-1-5386-7181-8

T3 - IEEE nternational Conference on Biometrics Theory, Applications and Systems (BTAS)

BT - 2018 IEEE 9th International Conference on Biometrics Theory, Applications and Systems, BTAS 2018

PB - IEEE

CY - Piscataway, NJ

ER -

Zeinstra C, Meuwly D, Veldhuis R, Spreeuwers L. Mind the Gap: A practical framework for classifiers in a forensic context. In 2018 IEEE 9th International Conference on Biometrics Theory, Applications and Systems, BTAS 2018. Piscataway, NJ: IEEE. 2019. 8698583. (IEEE nternational Conference on Biometrics Theory, Applications and Systems (BTAS)). https://doi.org/10.1109/BTAS.2018.8698583