An approaches for noise induced object classifications accuracy improvement

Eric K. Davis; Uttam Majumder; Chris Capraro; Chris Cicotta; Josh Siddall; Dan Brown

doi:10.1117/12.2520618

31 May 2019 An approaches for noise induced object classifications accuracy improvement

Eric K. Davis, Uttam Majumder, Chris Capraro, Chris Cicotta, Josh Siddall, Dan Brown

Proceedings Volume 11011, Cyber Sensing 2019; 110110A (2019) https://doi.org/10.1117/12.2520618
Event: SPIE Defense + Commercial Sensing, 2019, Baltimore, MD, United States

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.

Conference Presentation

Citation Download Citation

Eric K. Davis, Uttam Majumder, Chris Capraro, Chris Cicotta, Josh Siddall, and Dan Brown "An approaches for noise induced object classifications accuracy improvement", Proc. SPIE 11011, Cyber Sensing 2019, 110110A (31 May 2019); https://doi.org/10.1117/12.2520618

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