Decision-fusion-based automated drill bit toolmark correlator

Brett C. Jones; Michael J. Press; Joseph R. Guerci

doi:10.1117/12.334536

4 February 1999 Decision-fusion-based automated drill bit toolmark correlator

Brett C. Jones, Michael J. Press, Joseph R. Guerci

Proceedings Volume 3576, Investigation and Forensic Science Technologies; (1999) https://doi.org/10.1117/12.334536
Event: Enabling Technologies for Law Enforcement and Security, 1998, Boston, MA, United States

Abstract

This paper describes a recent study conducted to investigate the reproducibility of toolmarks left by drill bits. This paper focuses on the automated analysis aspect of the study, and particularly the advantages of using decision fusion methods in the comparisons. To enable the study to encompass a large number of samples, existing technology was adapted to the task of automatically comparing the test impressions. Advanced forensic pattern recognition algorithms that had been developed for the comparison of ballistic evidence in the DRUGFIRE^TM system were modified for use in this test. The results of the decision fusion architecture closely matched those obtained by expert visual examination. The study, aided by the improved pattern recognition algorithm, showed that drill bit impressions do contain reproducible marks. In a blind test, the DRUGFIRE pattern recognition algorithm, enhanced with the decision fusion architecture, consistently identified the correct bit as the source of the test impressions.

Citation Download Citation

Brett C. Jones, Michael J. Press, and Joseph R. Guerci "Decision-fusion-based automated drill bit toolmark correlator", Proc. SPIE 3576, Investigation and Forensic Science Technologies, (4 February 1999); https://doi.org/10.1117/12.334536

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available