An AFIS Candidate List Centric Fingerprint Likelihood Ratio Model based on Morphometric and Spatial Analyses (MSA)

Joshua Abraham, Paul Kwan, Christophe Champod, Christopher Lennard, Claude Roux

Research output: A Conference proceeding or a Chapter in BookChapter

Abstract

In this chapter, we will firstly discuss the current state of forensic fingerprint identification and how models play an important role for the future, followed by a brief introduction and review into relevant statistical models. Next, we will introduce a Likelihood Ratio (LR) model based on Support Vector Machines (SVMs) trained with features discovered via the morphometric and other spatial analyses of matching minutiae for both genuine and close imposter (or match and close non-match) populations typically recovered from Automated Fingerprint Identification System (AFIS) candidate lists. Lastly, experimentation performed on a set of over 60,000 publicly available fingerprint images (mostly sourced from NIST and FVC databases) and a distortion set of 6,000 images will be presented, illustrating that the proposed LR model is reliably guiding towards the right proposition in the identification assessment for both genuine and high ranking imposter populations, based on the discovered distortion characteristic differences of each population.
Original languageEnglish
Title of host publicationNew Trends and Developments in Biometrics
EditorsJucheng Yang, Shan Juan Xie
Place of PublicationUnited States
PublisherIn-Tech
Pages221-250
Number of pages30
Edition1st
ISBN (Print)9789535108597
Publication statusPublished - 2012

Fingerprint

Identification (control systems)
Support vector machines
Statistical Models

Cite this

Abraham, J., Kwan, P., Champod, C., Lennard, C., & Roux, C. (2012). An AFIS Candidate List Centric Fingerprint Likelihood Ratio Model based on Morphometric and Spatial Analyses (MSA). In J. Yang, & S. J. Xie (Eds.), New Trends and Developments in Biometrics (1st ed., pp. 221-250). United States: In-Tech.
Abraham, Joshua ; Kwan, Paul ; Champod, Christophe ; Lennard, Christopher ; Roux, Claude. / An AFIS Candidate List Centric Fingerprint Likelihood Ratio Model based on Morphometric and Spatial Analyses (MSA). New Trends and Developments in Biometrics. editor / Jucheng Yang ; Shan Juan Xie. 1st. ed. United States : In-Tech, 2012. pp. 221-250
@inbook{e6615d5b6ec744f3b955e7f8ca063c99,
title = "An AFIS Candidate List Centric Fingerprint Likelihood Ratio Model based on Morphometric and Spatial Analyses (MSA)",
abstract = "In this chapter, we will firstly discuss the current state of forensic fingerprint identification and how models play an important role for the future, followed by a brief introduction and review into relevant statistical models. Next, we will introduce a Likelihood Ratio (LR) model based on Support Vector Machines (SVMs) trained with features discovered via the morphometric and other spatial analyses of matching minutiae for both genuine and close imposter (or match and close non-match) populations typically recovered from Automated Fingerprint Identification System (AFIS) candidate lists. Lastly, experimentation performed on a set of over 60,000 publicly available fingerprint images (mostly sourced from NIST and FVC databases) and a distortion set of 6,000 images will be presented, illustrating that the proposed LR model is reliably guiding towards the right proposition in the identification assessment for both genuine and high ranking imposter populations, based on the discovered distortion characteristic differences of each population.",
keywords = "Forensic Science, Fingerprint Identification, Statistical Models",
author = "Joshua Abraham and Paul Kwan and Christophe Champod and Christopher Lennard and Claude Roux",
year = "2012",
language = "English",
isbn = "9789535108597",
pages = "221--250",
editor = "Jucheng Yang and Xie, {Shan Juan}",
booktitle = "New Trends and Developments in Biometrics",
publisher = "In-Tech",
edition = "1st",

}

Abraham, J, Kwan, P, Champod, C, Lennard, C & Roux, C 2012, An AFIS Candidate List Centric Fingerprint Likelihood Ratio Model based on Morphometric and Spatial Analyses (MSA). in J Yang & SJ Xie (eds), New Trends and Developments in Biometrics. 1st edn, In-Tech, United States, pp. 221-250.

An AFIS Candidate List Centric Fingerprint Likelihood Ratio Model based on Morphometric and Spatial Analyses (MSA). / Abraham, Joshua; Kwan, Paul; Champod, Christophe; Lennard, Christopher; Roux, Claude.

New Trends and Developments in Biometrics. ed. / Jucheng Yang; Shan Juan Xie. 1st. ed. United States : In-Tech, 2012. p. 221-250.

Research output: A Conference proceeding or a Chapter in BookChapter

TY - CHAP

T1 - An AFIS Candidate List Centric Fingerprint Likelihood Ratio Model based on Morphometric and Spatial Analyses (MSA)

AU - Abraham, Joshua

AU - Kwan, Paul

AU - Champod, Christophe

AU - Lennard, Christopher

AU - Roux, Claude

PY - 2012

Y1 - 2012

N2 - In this chapter, we will firstly discuss the current state of forensic fingerprint identification and how models play an important role for the future, followed by a brief introduction and review into relevant statistical models. Next, we will introduce a Likelihood Ratio (LR) model based on Support Vector Machines (SVMs) trained with features discovered via the morphometric and other spatial analyses of matching minutiae for both genuine and close imposter (or match and close non-match) populations typically recovered from Automated Fingerprint Identification System (AFIS) candidate lists. Lastly, experimentation performed on a set of over 60,000 publicly available fingerprint images (mostly sourced from NIST and FVC databases) and a distortion set of 6,000 images will be presented, illustrating that the proposed LR model is reliably guiding towards the right proposition in the identification assessment for both genuine and high ranking imposter populations, based on the discovered distortion characteristic differences of each population.

AB - In this chapter, we will firstly discuss the current state of forensic fingerprint identification and how models play an important role for the future, followed by a brief introduction and review into relevant statistical models. Next, we will introduce a Likelihood Ratio (LR) model based on Support Vector Machines (SVMs) trained with features discovered via the morphometric and other spatial analyses of matching minutiae for both genuine and close imposter (or match and close non-match) populations typically recovered from Automated Fingerprint Identification System (AFIS) candidate lists. Lastly, experimentation performed on a set of over 60,000 publicly available fingerprint images (mostly sourced from NIST and FVC databases) and a distortion set of 6,000 images will be presented, illustrating that the proposed LR model is reliably guiding towards the right proposition in the identification assessment for both genuine and high ranking imposter populations, based on the discovered distortion characteristic differences of each population.

KW - Forensic Science

KW - Fingerprint Identification

KW - Statistical Models

M3 - Chapter

SN - 9789535108597

SP - 221

EP - 250

BT - New Trends and Developments in Biometrics

A2 - Yang, Jucheng

A2 - Xie, Shan Juan

PB - In-Tech

CY - United States

ER -

Abraham J, Kwan P, Champod C, Lennard C, Roux C. An AFIS Candidate List Centric Fingerprint Likelihood Ratio Model based on Morphometric and Spatial Analyses (MSA). In Yang J, Xie SJ, editors, New Trends and Developments in Biometrics. 1st ed. United States: In-Tech. 2012. p. 221-250