Share Email Print
cover

Proceedings Paper

An approaches for noise induced object classifications accuracy improvement
Author(s): Eric K. Davis; Uttam Majumder; Chris Capraro; Chris Cicotta; Josh Siddall; Dan Brown
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Among various parameters, large scene object detection and classification accuracy depends on image quality. In general, deep neural networks (DNN) are trained to achieve a desired recognition accuracy on a set of targets. However, DNNs become tuned to the training data used and may not generalize to new unseen data artifacts. Classification accuracy of a previously trained DNN is significantly reduced when classification is run on an image altered with additive noise. In this research, we propose image pre-processing to reduce the impact of noise induced low classification accuracy. Our approach consists of applying compressive sensing inspired pre-processing techniques to noisy images. We then compare the object recognition accuracy of a pretrained model on pre-processed noisy images and unprocessed noisy images. We will present our technical method, results, and analysis on relevant synthetic aperture radar data.

Paper Details

Date Published: 31 May 2019
PDF: 10 pages
Proc. SPIE 11011, Cyber Sensing 2019, 110110A (31 May 2019); doi: 10.1117/12.2520618
Show Author Affiliations
Eric K. Davis, SRC Inc. (United States)
Uttam Majumder, Air Force Research Lab. (United States)
Chris Capraro, SRC Inc. (United States)
Chris Cicotta, SRC Inc. (United States)
Josh Siddall, SRC Inc. (United States)
Dan Brown, SRC Inc. (United States)


Published in SPIE Proceedings Vol. 11011:
Cyber Sensing 2019
Igor V. Ternovskiy; Peter Chin, Editor(s)

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