Logo des Repositoriums

Auflistung nach Schlagwort "Biometric features"

1 - 2 von 2
  • Konferenzbeitrag
    Analysing Distributions of Feature Similarities in the Context of Digital Anthropometric Pattern Matching Probability
    (INFORMATIK 2023 - Designing Futures: Zukünfte gestalten, 2023) Heinke, Florian; Heuschkel, Marie-Luise; Labudde, Dirk
    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.
  • Textdokument
    A frequentist estimation of duplicate probability as a baseline for person identification from image and video material using anthropometric measurements
    (INFORMATIK 2022, 2022) Heinke,Florian; Heuschkel,Marie-Luise; Labudde,Dirk
    Video and image material is becoming increasingly ubiquitous thus its potential as evidence in forensic investigations is growing. Once faces are hidden however, the value of surveillance footage is restricted unless there is another biometric trait that can be observed by camera such as linear body measurements. There is much biological evidence for human body proportions exhibiting much individual variation. Nevertheless, the probability of there being two individuals that match in their respective proportions ultimately determines its usability for the assignment, exclusion and even identification of persons in the forensic domain. This work is concerned with approaches for duplicate probability estimations derived from anthropometric measures. Here, we present a novel frequentist estimation using a dataset of 340 individuals and their respective anthropometric measurements. Drawing on density kernel estimations of measurement dissimilarity, we propose the duplicate probability to be in the order of 10^−15 to 10^−8.