Impact of optical scatter on image classification with deep neural networks

Page King; R. John Koshel

doi:10.1117/12.2672633

10 October 2023 Impact of optical scatter on image classification with deep neural networks

Page King, R. John Koshel

Proceedings Volume 12675, Applications of Machine Learning 2023; 1267508 (2023) https://doi.org/10.1117/12.2672633
Event: SPIE Optical Engineering + Applications, 2023, San Diego, California, United States

Abstract

Robustness to image quality degradations is critical for developing Deep Neural Networks (DNNs) for real-world image classification. Prior work explored how various optical aberrations degrade image classification performance [1]. This paper extends this discussion to include optical scatter, which is fundamental to the stray light control of imaging systems and enables further discussion of DNN performance in the context of hardware design. In this paper, multiple state-of-the-art DNN models are evaluated for their image classification performance with imagery that has been degraded by optical scatter.

Conference Presentation

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Page King and R. John Koshel "Impact of optical scatter on image classification with deep neural networks", Proc. SPIE 12675, Applications of Machine Learning 2023, 1267508 (10 October 2023); https://doi.org/10.1117/12.2672633

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