Share Email Print

Proceedings Paper

Interactive target recognition in images using machine-learning techniques
Author(s): Ariel Michaeli; Irit Camon
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Imagery analysis systems utilize Automatic Target Recognition (ATR) methods in order to improve the accuracy of human-based analysis and save time. Often, ATR methods perform poorly in obtaining these objectives, due to reliance on outdated prior information, while human operators possess updated information that remains unused. This paper presents an interactive target recognition (or ITR) application. The operator marks sample target pixels by an intuitive user-interface. Then machine-learning techniques generate algorithms tailored for their recognition in imagery. The resulting detection map is dynamically controlled by the operator, suiting his needs. The application enables target recognition in zero prior information environments.

Paper Details

Date Published: 5 May 2011
PDF: 6 pages
Proc. SPIE 8050, Signal Processing, Sensor Fusion, and Target Recognition XX, 80501B (5 May 2011); doi: 10.1117/12.884972
Show Author Affiliations
Ariel Michaeli, RAFAEL Advanced Defense Systems Ltd. (Israel)
Irit Camon, RAFAEL Advanced Defense Systems Ltd. (Israel)

Published in SPIE Proceedings Vol. 8050:
Signal Processing, Sensor Fusion, and Target Recognition XX
Ivan Kadar, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?