Performance metrics for the evaluation of hyperspectral chemical identification systems

Eric Truslow; Steven E. Golowich; Dimitris G. Manolakis; Vinay K. Ingle

doi:10.1117/1.OE.55.2.023106

10 February 2016 Performance metrics for the evaluation of hyperspectral chemical identification systems

Eric Truslow, Steven E. Golowich, Dimitris G. Manolakis, Vinay K. Ingle

Author Affiliations +

Optical Engineering, Vol. 55, Issue 2, 023106 (February 2016). https://doi.org/10.1117/1.OE.55.2.023106

Abstract

Remote sensing of chemical vapor plumes is a difficult but important task for many military and civilian applications. Hyperspectral sensors operating in the long-wave infrared regime have well-demonstrated detection capabilities. However, the identification of a plume’s chemical constituents, based on a chemical library, is a multiple hypothesis testing problem which standard detection metrics do not fully describe. We propose using an additional performance metric for identification based on the so-called Dice index. Our approach partitions and weights a confusion matrix to develop both the standard detection metrics and identification metric. Using the proposed metrics, we demonstrate that the intuitive system design of a detector bank followed by an identifier is indeed justified when incorporating performance information beyond the standard detection metrics.

Citation Download Citation

Eric Truslow, Steven E. Golowich, Dimitris G. Manolakis, and Vinay K. Ingle "Performance metrics for the evaluation of hyperspectral chemical identification systems," Optical Engineering 55(2), 023106 (10 February 2016). https://doi.org/10.1117/1.OE.55.2.023106

Published: 10 February 2016

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