Konferenzbeitrag
Analysing Distributions of Feature Similarities in the Context of Digital Anthropometric Pattern Matching Probability
Lade...
Volltext URI
Dokumententyp
Text/Conference Paper
Zusatzinformation
Datum
2023
Autor:innen
Zeitschriftentitel
ISSN der Zeitschrift
Bandtitel
Verlag
Gesellschaft für Informatik e.V.
Zusammenfassung
Digital anthropometric pattern matching encompasses biometric identification on the basis of a combination of anthropometric measurements depicting the proportions of the human body from image or video material. In a previous publication, maximum likelihood density estimation of distributions of anthropometric measurement distances allowed for estimation of the probability of a match to be in the order of 10−15 to 10−8. However, the underlying nature and cause of these distributions remained unclear. This work represents an enhancement allowing for an analytical description of these distributions by assuming multivariate normals as distributions models, and by estimating distribution parameters that subsequently allow reasonable probability approximations. Thus the methodological groundwork presented here contributes to the evaluation of the probability for obtaining a match.