Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

A novel and robust deep learning model for sibling firearm matching.

Efe Arin1, I Samil Yetik2

  • 1Department of Electrical and Electronics Engineering, Gazi University, Ankara, Türkiye; Department of Electrical and Electronics Engineering, TOBB University of Economics and Technology, Ankara, Türkiye.

Forensic Science International
|July 1, 2026
PubMed
Summary

Related Concept Videos

Force Classification01:22

Force Classification

Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Direct regularized estimation of retinal vascular oxygen tension based on an experimental model.

Annals of biomedical engineering·2013
See all related articles

This study introduces a new method for firearm sibling matching using cartridge case imagery. The novel approach significantly improves accuracy in identifying matching cartridge cases, outperforming previous methods.

Area of Science:

  • Forensic Science
  • Computer Vision
  • Pattern Recognition

Background:

  • Firearm sibling matching is crucial for forensic investigations.
  • Existing methods struggle with real-world data complexity, including aged or modified firearms.
  • Photometric stereo imagery of cartridge case heads offers detailed surface information.

Purpose of the Study:

  • To develop a novel and robust method for firearm sibling matching using photometric stereo imagery of cartridge case heads.
  • To address the challenges posed by diverse and complex real-world forensic datasets.
  • To advance the state-of-the-art in cartridge case matching.

Main Methods:

  • Development of a triplet-loss framework with semi-hard negative mining and an explicit margin term.
Keywords:
Ballistic individualizationBallistic photometric stereoDeep learningFirearm sibling matchingFiring pin impression matching

Related Experiment Videos

  • Integration of a pre-contrastive loss, a novel approach for this domain.
  • Benchmarking against a deep model utilizing pure contrastive loss.

    • Main Results:

    • The proposed model significantly outperforms the contrastive loss model.
    • Achieved 90% success rate in identifying siblings within the top 20 candidates.
    • The contrastive model achieved only 52% success in the same test conditions.

    Conclusions:

    • The study presents the strongest contribution to cartridge-case sibling matching in the literature.
    • The novel methodology demonstrates superior performance on realistic and challenging datasets.
    • The findings have significant implications for forensic firearm identification.