Neural network for intelligent query of an FBI forensic database

Lee A. Uvanni; Timothy G. Rainey; Uma Balasubramanian; Dean W. Brettle; Fred Weingard; Robert W. Sibert; Eric Birnbaum

doi:10.1117/12.266749

18 February 1997 Neural network for intelligent query of an FBI forensic database

Lee A. Uvanni, Timothy G. Rainey, Uma Balasubramanian, Dean W. Brettle, Fred Weingard, Robert W. Sibert, Eric Birnbaum

Proceedings Volume 2938, Command, Control, Communications, and Intelligence Systems for Law Enforcement; (1997) https://doi.org/10.1117/12.266749
Event: Enabling Technologies for Law Enforcement and Security, 1996, Boston, MA, United States

Abstract

Examiner is an automated fired cartridge case identification system utilizing a dual-use neural network pattern recognition technology, called the statistical-multiple object detection and location system (S-MODALS) developed by Booz(DOT)Allen & Hamilton, Inc. in conjunction with Rome Laboratory. S-MODALS was originally designed for automatic target recognition (ATR) of tactical and strategic military targets using multisensor fusion [electro-optical (EO), infrared (IR), and synthetic aperture radar (SAR)] sensors. Since S-MODALS is a learning system readily adaptable to problem domains other than automatic target recognition, the pattern matching problem of microscopic marks for firearms evidence was analyzed using S-MODALS. The physics; phenomenology; discrimination and search strategies; robustness requirements; error level and confidence level propagation that apply to the pattern matching problem of military targets were found to be applicable to the ballistic domain as well. The Examiner system uses S-MODALS to rank a set of queried cartridge case images from the most similar to the least similar image in reference to an investigative fired cartridge case image. The paper presents three independent tests and evaluation studies of the Examiner system utilizing the S-MODALS technology for the Federal Bureau of Investigation.

Citation Download Citation

Lee A. Uvanni, Timothy G. Rainey, Uma Balasubramanian, Dean W. Brettle, Fred Weingard, Robert W. Sibert, and Eric Birnbaum "Neural network for intelligent query of an FBI forensic database", Proc. SPIE 2938, Command, Control, Communications, and Intelligence Systems for Law Enforcement, (18 February 1997); https://doi.org/10.1117/12.266749

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