Spatial analysis of corresponding fingerprint features from match and close non-match populations

Joshua Abraham, Christophe Champod, Chris LENNARD, Claude Roux

    Research output: Contribution to journalArticle

    6 Citations (Scopus)

    Abstract

    The development of statistical models for forensic fingerprint identification purposes has been the subject of increasing research attention in recent years. This can be partly seen as a response to a number of commentators who claim that the scientific basis for fingerprint identification has not been adequately demonstrated. In addition, key forensic identification bodies such as ENFSI [1] and IAI [2] have recently endorsed and acknowledged the potential benefits of using statistical models as an important tool in support of the fingerprint identification process within the ACE-V framework.

    In this paper, we introduce a new Likelihood Ratio (LR) model based on Support Vector Machines (SVMs) trained with features discovered via morphometric and spatial analyses of corresponding minutiae configurations for both match and close non-match populations often found in AFIS candidate lists. Computed LR values are derived from a probabilistic framework based on SVMs that discover the intrinsic spatial differences of match and close non-match populations. Lastly, experimentation performed on a set of over 120,000 publicly available fingerprint images (mostly sourced from the National Institute of Standards and Technology (NIST) datasets) and a distortion set of approximately 40,000 images, is presented, illustrating that the proposed LR model is reliably guiding towards the right proposition in the identification assessment of match and close non-match populations. Results further indicate that the proposed model is a promising tool for fingerprint practitioners to use for analysing the spatial consistency of corresponding minutiae configurations
    Original languageEnglish
    Pages (from-to)87-98
    Number of pages12
    JournalForensic Science International
    Volume230
    Issue number1-3
    DOIs
    Publication statusPublished - 2013

    Fingerprint

    Spatial Analysis
    Dermatoglyphics
    Population
    Statistical Models
    Technology
    Research

    Cite this

    Abraham, Joshua ; Champod, Christophe ; LENNARD, Chris ; Roux, Claude. / Spatial analysis of corresponding fingerprint features from match and close non-match populations. In: Forensic Science International. 2013 ; Vol. 230, No. 1-3. pp. 87-98.
    @article{2bab8f893f3f474ab8bad210a1455d50,
    title = "Spatial analysis of corresponding fingerprint features from match and close non-match populations",
    abstract = "The development of statistical models for forensic fingerprint identification purposes has been the subject of increasing research attention in recent years. This can be partly seen as a response to a number of commentators who claim that the scientific basis for fingerprint identification has not been adequately demonstrated. In addition, key forensic identification bodies such as ENFSI [1] and IAI [2] have recently endorsed and acknowledged the potential benefits of using statistical models as an important tool in support of the fingerprint identification process within the ACE-V framework. In this paper, we introduce a new Likelihood Ratio (LR) model based on Support Vector Machines (SVMs) trained with features discovered via morphometric and spatial analyses of corresponding minutiae configurations for both match and close non-match populations often found in AFIS candidate lists. Computed LR values are derived from a probabilistic framework based on SVMs that discover the intrinsic spatial differences of match and close non-match populations. Lastly, experimentation performed on a set of over 120,000 publicly available fingerprint images (mostly sourced from the National Institute of Standards and Technology (NIST) datasets) and a distortion set of approximately 40,000 images, is presented, illustrating that the proposed LR model is reliably guiding towards the right proposition in the identification assessment of match and close non-match populations. Results further indicate that the proposed model is a promising tool for fingerprint practitioners to use for analysing the spatial consistency of corresponding minutiae configurations",
    keywords = "Candidate lists, Fingerprint identification, Likelihood ratio, Spatial analysis, Statistical models",
    author = "Joshua Abraham and Christophe Champod and Chris LENNARD and Claude Roux",
    year = "2013",
    doi = "10.1016/j.forsciint.2012.10.034",
    language = "English",
    volume = "230",
    pages = "87--98",
    journal = "Forensic Science",
    issn = "0379-0738",
    publisher = "Elsevier Ireland Ltd",
    number = "1-3",

    }

    Spatial analysis of corresponding fingerprint features from match and close non-match populations. / Abraham, Joshua; Champod, Christophe; LENNARD, Chris; Roux, Claude.

    In: Forensic Science International, Vol. 230, No. 1-3, 2013, p. 87-98.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - Spatial analysis of corresponding fingerprint features from match and close non-match populations

    AU - Abraham, Joshua

    AU - Champod, Christophe

    AU - LENNARD, Chris

    AU - Roux, Claude

    PY - 2013

    Y1 - 2013

    N2 - The development of statistical models for forensic fingerprint identification purposes has been the subject of increasing research attention in recent years. This can be partly seen as a response to a number of commentators who claim that the scientific basis for fingerprint identification has not been adequately demonstrated. In addition, key forensic identification bodies such as ENFSI [1] and IAI [2] have recently endorsed and acknowledged the potential benefits of using statistical models as an important tool in support of the fingerprint identification process within the ACE-V framework. In this paper, we introduce a new Likelihood Ratio (LR) model based on Support Vector Machines (SVMs) trained with features discovered via morphometric and spatial analyses of corresponding minutiae configurations for both match and close non-match populations often found in AFIS candidate lists. Computed LR values are derived from a probabilistic framework based on SVMs that discover the intrinsic spatial differences of match and close non-match populations. Lastly, experimentation performed on a set of over 120,000 publicly available fingerprint images (mostly sourced from the National Institute of Standards and Technology (NIST) datasets) and a distortion set of approximately 40,000 images, is presented, illustrating that the proposed LR model is reliably guiding towards the right proposition in the identification assessment of match and close non-match populations. Results further indicate that the proposed model is a promising tool for fingerprint practitioners to use for analysing the spatial consistency of corresponding minutiae configurations

    AB - The development of statistical models for forensic fingerprint identification purposes has been the subject of increasing research attention in recent years. This can be partly seen as a response to a number of commentators who claim that the scientific basis for fingerprint identification has not been adequately demonstrated. In addition, key forensic identification bodies such as ENFSI [1] and IAI [2] have recently endorsed and acknowledged the potential benefits of using statistical models as an important tool in support of the fingerprint identification process within the ACE-V framework. In this paper, we introduce a new Likelihood Ratio (LR) model based on Support Vector Machines (SVMs) trained with features discovered via morphometric and spatial analyses of corresponding minutiae configurations for both match and close non-match populations often found in AFIS candidate lists. Computed LR values are derived from a probabilistic framework based on SVMs that discover the intrinsic spatial differences of match and close non-match populations. Lastly, experimentation performed on a set of over 120,000 publicly available fingerprint images (mostly sourced from the National Institute of Standards and Technology (NIST) datasets) and a distortion set of approximately 40,000 images, is presented, illustrating that the proposed LR model is reliably guiding towards the right proposition in the identification assessment of match and close non-match populations. Results further indicate that the proposed model is a promising tool for fingerprint practitioners to use for analysing the spatial consistency of corresponding minutiae configurations

    KW - Candidate lists

    KW - Fingerprint identification

    KW - Likelihood ratio

    KW - Spatial analysis

    KW - Statistical models

    U2 - 10.1016/j.forsciint.2012.10.034

    DO - 10.1016/j.forsciint.2012.10.034

    M3 - Article

    VL - 230

    SP - 87

    EP - 98

    JO - Forensic Science

    JF - Forensic Science

    SN - 0379-0738

    IS - 1-3

    ER -