Logo des Repositoriums

Auflistung nach Autor:in "Labudde, Dirk"

1 - 10 von 18
  • 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.
  • Konferenzbeitrag
    Analysis of X-ray images of femora for age of death estimation of skeletal individuals
    (Biosig 2016, 2016) Jeraufke, Saskia; Pflugbeil, Anne-Marie; Becker, Sven; Schildbach, Stefan; Bruchhaus, Horst; Thiele, Karlheinz; Dreßler, Jan; Labudde, Dirk
  • Textdokument
    Automated Determination of Fingerprint Ridge Density and Fingerprint Size to Detect Sex Differences
    (INFORMATIK 2021, 2021) Mohaupt, Marleen; Stoeter, Sieke; Labudde, Dirk
    A fingerprint is probably the most important biometric feature when trying to link a suspect to a crime scene. So far, without a hit in a fingerprint database, it was impossible to use a collected fingerprint to narrow down the group of suspects. Moreover, in the existing studies about deriving phenotypic characteristics from fingerprints the analyses were done manually. In contrast, in this paper a procedure is presented to automatically determine the fingerprint ridge density and the fingerprint size, in order to derive information about the sex of the person the fingerprint belongs to. All 10 fingerprints of 140 individuals (70 males and 70 females) belonging to the German Caucasian population were secured and then analyzed. The best result was obtained for the ulnar area in combination with the fingerprint size of the left thumb with F1 measures of 0.84 (k-nearest neighbors algorithm - KNN), 0.833 (Support Vector Machine) and 0.817 (logistic regression).
  • Zeitschriftenartikel
    Automatic Classification of Bloodstains with Deep Learning Methods
    (KI - Künstliche Intelligenz: Vol. 36, No. 2, 2022) Bergman, Tommy; Klöden, Martin; Dreßler, Jan; Labudde, Dirk
    The classification of detected bloodstains into predetermined categories is a crucial component of the so-called bloodstain pattern analysis. As in other forensic disciplines, deep learning methods may help to reduce human subjectivity within this process, may increase the classification accuracy, shorten the calculation time and thus, enable high-throughput analysis. In this work, an approach is presented in which a convolutional neural network (Inception v3) was trained from 965 drip stains (passive origin) and 1595 blood spatters (active origin). The trained CNN was evaluated with a test data set consisting of 366 images of drip stains and blood spatters. The success rate was 99.73% which suggests that neural networks could also be used to automatically classify other classes of bloodstain patterns to speed up the investigation process in the future.
  • Zeitschriftenartikel
    COMBI: Artificial Intelligence for Computer-Based Forensic Analysis of Persons
    (KI - Künstliche Intelligenz: Vol. 36, No. 2, 2022) Becker, Sven; Heuschkel, Marie; Richter, Sabine; Labudde, Dirk
    During the prosecution process the primary objective is to prove criminal offences to the correct perpetrator to convict them with legal effect. However, in reality this may often be difficult to achieve. Suppose a suspect has been identified and is accused of a bank robbery. Due to the location of the crime, it can be assumed that there is sufficient image and video surveillance footage available, having recorded the perpetrator at the crime scene. Depending on the surveillance system used, there could be even high-resolution material available. In short, optimal conditions seem to be in place for further investigations, especially as far as the identification of the perpetrator and the collection of evidence of their participation in the crime are concerned. However, perpetrators usually act using some kind of concealment to hide their identity. In most cases, they disguise their faces and even their gait. Conventional investigation approaches and methods such as facial recognition and gait analysis then quickly reach their limits. For this reason, an approach based on anthropometric person-specific digital skeletons, so-called rigs, that is being researched by the COMBI research project is presented in this publication. Using these rigs, it should be possible to assign known identities, comparable to suspects, to unknown identities, comparable to perpetrators. The aim of the COMBI research project is to study the anthropometric pattern as a biometric identifier as well as to make it feasible for the standardised application in the taking of evidence by the police and prosecution. The approach is intended to present computer-aided opportunities for the identification of perpetrators that can support already established procedures.
  • Konferenzbeitrag
    Deepfakes als Beweismittel: Zur Notwendigkeit der Authentizitätsprüfung von Bild- , Audio- und Videodaten: Das digitale Rig als Authentifizierungsmethode zur Erkennung von synthetischen Bild- und Videodaten
    (INFORMATIK 2024, 2024) Kellermann, Stefan; Labudde, Dirk
    Mit der zunehmenden Leistungsfähigkeit von künstlicher Intelligenz werden die Anforderungen an eine Authentizitätsprüfung von Bild-, Audio-, und Videodaten unter anderem bei der Verwendung der Inhalte als Beweismittel für die Strafverfolgungsbehörden steigen. Dass der Gesetzgeber darüber hinaus exemplarisch bei der Protokollierung von Strafermittlungsverfahren auf Videodaten (Videovernehmungen) oder Audiodaten (Aufzeichnung von Gerichtsverhandlungen) auf die Integrität dieser setzt, zeigen die Gesetzesänderungen der letzten Jahre. Bei zunehmender Verbreitung von synthetischen (KI-generierten) Inhalten muss es für forensische Untersuchungen verlässlich möglich sein, synthetische Inhalte zu erkennen, um die Authentizität der Daten beweissicher bewerten zu können. In dieser Arbeit wird auf verschiedene Techniken der Herstellung von Deepfakes und grundsätzliche Ansatzpunkte der Detektion eingegangen. Das digitale Rig wird als Möglichkeit zur Authentizitätsprüfung bei body-puppetry-Imitationen vorgestellt und als KI-Anwendung selbst in den EU-gesetzlichen Kontext des EU AI Actes gesetzt.
  • Konferenzbeitrag
    Development and empirical optimization of an electrochemical analysis cell for the visualization of latent fingerprints and their chemical adhesives
    (BIOSIG 2020 - Proceedings of the 19th International Conference of the Biometrics Special Interest Group, 2020) Bergmann, Tommy; Gottschall, Sebastian; Fuchs, Enrico; Berlipp, Oliver; Labudde, Dirk
    Fingerprint analysis played a major role in the investigation of criminal offences for the past 100 years and is often the sole means of criminal identification [YA04]. Electrochemical analysis can yield important additional evidence like fingerprint age, biological age and gender of its creator as well as chemical adhesives [GRW12]. Additional gained characteristics through electrochemical analysis can supplement latent or incomplete fingerprints. In previous work a ruthenium-complex based solution was used as illuminant. Since luminol is readily available and is used in many forensic applications, the presented paper will focus on luminol as an alternative chemical for the ECL-aided visualization of fingerprints. Experiments were conducted by creating an electrochemical reaction inside a purpose build analysis cell. Eccrine, sebaceous glandlike and vaseline contaminated fingerprints were created on a stainless-steel plate placed inside the cell and investigated while applying direct current. Aim of this research was to investigate which kind of fingerprints can be visualized and which quality of the resulting images can be reached using luminol as illuminant. The used laboratory power supply created a strong light reaction at the start of each experiment revealing potential for further enhancement of the image quality. Eccrine dactyloscopic evidence showed no visible results. For sebaceous glandlike fingerprints age was discovered to significantly influence image quality.
  • Konferenzbeitrag
    The digital skeleton in modern video analysis - inter- and intraspecific comparsionofindividualrigs
    (INFORMATIK 2023 - Designing Futures: Zukünfte gestalten, 2023) Pistorius, Elena; Richter, Sabine; Labudde, Dirk
    New methods for identifying individuals based on their digital skeleton (rig) gain attention in digital forensics. To ensure a solid comparison, understanding the development of this digital skeleton is crucial. One approach is manually creating a rig using a parametrized 3D room and cameras with embedded pictures, capturing multiple angles of the same person with markers on defined spots. Using these pictures and the room, a movable marker-based rig can be built in software like Blender (https://www.blender.org). It can be used to fit the rigged doll into another scene or compare proportions. For a similar process, algorithm-based software like OpenPose (https://github.com/CMU- Perceptual-Computing-Lab/openpose) estimates a digital skeleton from pictures or videos. The output includes JSON files with joint coordinates and pictures with embedded skeletons, which can manually be processsed into a rig. While these procedure can save time and expand applications, precision and supervision differ from marker-based rigs. A comparative study assessing similarity is discussed in the following paper.
  • Zeitschriftenartikel
    Die Enkel von Locard
    (Informatik Spektrum: Vol. 44, No. 5, 2021) Povalej, Roman; Rittelmeier, Heiko; Fähndrich, Johannes; Berner, Silvio; Honekamp, Wilfried; Labudde, Dirk
    Die seit Jahrhunderten verwendeten Methoden in der Forensik basieren auf der Annahme eines Austausches von Materie und Mustern. Durch die Digitalisierung sind diese Annahmen nur noch eingeschränkt gültig und werden hier erweitert und diskutiert. In dem Zusammenhang ist es erforderlich, den Spurenbegriff grundlegend zu überdenken. Gleichzeitig werfen der ständige technische Fortschritt und die immer größer werdende Flut von auszuwertenden Daten die Ermittlungsbehörden immer wieder zurück. Dieser Entwicklung ist nur durch Automatisierung Herr zu werden. Verfahren der Künstlichen Intelligenz können und werden die Ermittlungsbehörden zukünftig dabei zunehmend unterstützen.
  • Konferenzbeitrag
    Der forensische Wert von Thumbnails und Cache-Dateien im Ermittlungsverfahren
    (INFORMATIK 2024, 2024) Herchel, Sabrina; Steinert, Mirijam; Dehne, Vivien; Labudde, Dirk
    In der IT-Forensik nehmen Thumbnails und Cache-Dateien als Beweismittel eine wichtige Rolle ein. Dies liegt insbesondere an ihrer Eigenschaft, automatisch generiert und temporär gespeichert zu werden. Dieser Artikel betrachtet die Verwendbarkeit dieser Datentypen in gerichtlichen Verfahren. Dabei werden die technischen Hintergründe sowie die forensischen Techniken zur Sicherung und Auswertung von Beweisen erläutert. Es ist essenziell für Ermittler, eine klare Unterscheidung zwischen Thumbnails und Cache-Dateien treffen zu können, da beide oft verschiedene Auskünfte über die Herkunft und Nutzung der Daten geben. Thumbnails sind in der Regel verkleinerte Ansichten von Bildern, während Cache-Dateien häufig Kopien von Webseiten oder anderen Medien beinhalten, die zur Beschleunigung des Zugriffs abgelegt werden. Diese Differenzierung gewinnt insbesondere bei Fragen zur Herkunft und zum Kontext der Daten an Bedeutung. Das Ziel ist es, die Bedeutung von Thumbnails und Cache-Dateien in der täglichen Fallarbeit zu erläutern, ihre Unterscheidbarkeit darzustellen und ihren Beitrag zur Beweisführung hervorzuheben.