Informative representation learning for automatic target recognition

Charles F. Hester; Kelly K. D. Risko

doi:10.1117/12.885031

19 May 2011 Informative representation learning for automatic target recognition

Charles F. Hester, Kelly K. D. Risko

Proceedings Volume 8049, Automatic Target Recognition XXI; 80490A (2011) https://doi.org/10.1117/12.885031
Event: SPIE Defense, Security, and Sensing, 2011, Orlando, Florida, United States

Abstract

Informative representations are those representations that do more than reconstruct the data; they have information embedded implicitly in them and are compressive for utilization in real-time Automatic Target Recognition. In this paper we create methods for embedding information in subspace bases through sparsity and information theoretic measures. We present a theory of informative bases and demonstrate some practical examples of basis learning using infrared imagery. We will employ sparsity and entropy measures to drive the learning process to extract the most informative representation and will draw relations between informative representations and the quadratic correlation filter.

Citation Download Citation

Charles F. Hester and Kelly K. D. Risko "Informative representation learning for automatic target recognition", Proc. SPIE 8049, Automatic Target Recognition XXI, 80490A (19 May 2011); https://doi.org/10.1117/12.885031

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