Skip to content

Using Machine Learning Methods to Predict Similarity of Striations on Bullet Lands

Conference/Workshop:
2020 Joint Statistical Meetings (JSM)
Published: 2020
Primary Author: Heike Hofmann
Secondary Authors: Alicia L. Carriquiry, Susan VanderPlas
Research Area: Firearms and Toolmarks

Recent advances in microscopy have made it possible to collect 3D topographic data, enabling virtual comparisons based on the collected 3D data next to traditional comparison microscopy. Automatic matching algorithms have been introduced for various scenarios, such as matching cartridge cases (Tai and Eddy 2018) or matching bullet striae (Hare et al. 2017b, Chu et al 2013, De Kinder and Bonfanti 1999). One key aspect of validating automatic matching algorithms is to evaluate the performance of the algorithm on external tests. Here, we are presenting a discussion of the performance of the matching algorithm (Hare et al. 2017b) in three studies. We are considering matching performance based on the Random forest score, cross correlation, and consecutive matching striae (CMS) at the land-to-land level and, using Sequential Average Maxima scores, also at the bullet-to bullet level. Cross correlation and Random Forest scores both result in perfect discrimination of same-source and different-source bullets. At the land-to-land level, discrimination (based on area under the curve, AUC) is excellent (> 0.90).

Related Resources

An Open-Source Implementation of the CMPS Algorithm for Assessing Similarity of Bullets

An Open-Source Implementation of the CMPS Algorithm for Assessing Similarity of Bullets

In this paper, we introduce the R package cmpsR, an open-source implementation of the Congruent Matching Profile Segments (CMPS) method developed at the National Institute of Standards and Technology (NIST)…
A Pipeline for Cartridge Case Comparisons

A Pipeline for Cartridge Case Comparisons

We introduce novel sub-procedures in the pre-processing, comparison and similarity feature steps. The sub-procedures result in an improved error rate compared to our implementation of the CMC method while also…
Affect of Manufacturer Finishing Methods on Subclass Characteristics Production on Breech Faces

Affect of Manufacturer Finishing Methods on Subclass Characteristics Production on Breech Faces

The following is a presentation given at Association for Firearms and Toolmarks (AFTE) (2022).
An Algorithm for Forensic Toolmark Comparisons

An Algorithm for Forensic Toolmark Comparisons

Forensic handheld toolmark examiners currently compare toolmarks (e.g. scratch marks on wire found as part of an explosive device, or on a door frame after someone broke into a house)…