Understanding the relationship between image quality and convolutional neural network performance

Austin C. Bergstrom; David W. Messinger

doi:10.1117/12.2618590

27 May 2022 Understanding the relationship between image quality and convolutional neural network performance

Austin C. Bergstrom, David W. Messinger

Proceedings Volume 12101, Pattern Recognition and Tracking XXXIII; 1210103 (2022) https://doi.org/10.1117/12.2618590
Event: SPIE Defense + Commercial Sensing, 2022, Orlando, Florida, United States

Abstract

Substantial research has explored methods to optimize convolutional neural networks (CNNs) for tasks such as image classification and object detection, but research into the image quality drivers of computer vision performance has been limited. Additionally, there are indications that image degradations such as blur and noise affect human visual interpretation and machine interpretation differently. The General Image Quality Equation (GIQE) predicts overhead image quality for human analysis using the the National Image Interpretability Rating Scale (NIIRS), but no such model exists to predict image quality for interpretation by CNNs. Here, we assess the relationship between image quality variables and convolutional neural network (CNN) performance using an information-theoretic framework. Specifically, we examine the impacts of resolution, blur, and noise on CNN performance for models trained with in-distribution and out-of-distribution distortions. We explore the relationships between CNN performance and image information content as measured by standard Shannon entropy and a similar metric based on image gradients. Using two datasets, we observe that while generalization remains a significant challenge for CNNs faced with out-of-distribution image distortions, CNN performance against low visual quality images remains strong with appropriate training, indicating the potential to expand the design trade space for sensors providing data to computer vision systems

Conference Presentation

Citation Download Citation

Austin C. Bergstrom and David W. Messinger "Understanding the relationship between image quality and convolutional neural network performance", Proc. SPIE 12101, Pattern Recognition and Tracking XXXIII, 1210103 (27 May 2022); https://doi.org/10.1117/12.2618590

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