Translator Disclaimer
18 February 1997 Neural network for intelligent query of an FBI forensic database
Author Affiliations +
Proceedings Volume 2938, Command, Control, Communications, and Intelligence Systems for Law Enforcement; (1997)
Event: Enabling Technologies for Law Enforcement and Security, 1996, Boston, MA, United States
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.
© (1997) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
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);

Back to Top