Characterization of CNN classifier performance with respect to variation in optical contrast, using synthetic electro-optical data

Christopher Menart; Colin Leong; Olga Mendoza-Schrock; Edmund Zelnio

doi:10.1117/12.2519494

14 May 2019 Characterization of CNN classifier performance with respect to variation in optical contrast, using synthetic electro-optical data

Christopher Menart, Colin Leong, Olga Mendoza-Schrock, Edmund Zelnio

Author Affiliations +

Proceedings Volume 10988, Automatic Target Recognition XXIX; 109880N (2019) https://doi.org/10.1117/12.2519494
Event: SPIE Defense + Commercial Sensing, 2019, Baltimore, MD, United States

Abstract

Deep neural networks demonstrate high performance at classifying high-dimensional signals, but often fail to generalize to data that is different from the data they were trained on. In this paper, we investigate the resilience of convolutional neural networks (CNNs) to unforeseen operating conditions. Specifically, we empirically evaluate the ability of CNN models to generalize across changes in image contrast. Multiple models are trained on electro- optical (EO) or near-infrared (IR) data, and are evaluated in environments with degraded contrast compared to training. Experiments are replicated across varying architectures, including state-of-the-art classification models such as Resnet-152, and across both synthetic and measured datasets. In comparison to models trained and evaluated on identically-distributed data, these models can generalize well when contrast invariance is built up through data augmentation. Future work will investigate CNN ability to generalize to other changes in operating conditions.

Conference Presentation

Citation Download Citation

Christopher Menart, Colin Leong, Olga Mendoza-Schrock, and Edmund Zelnio "Characterization of CNN classifier performance with respect to variation in optical contrast, using synthetic electro-optical data", Proc. SPIE 10988, Automatic Target Recognition XXIX, 109880N (14 May 2019); https://doi.org/10.1117/12.2519494

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