Improving automatic text recognition through atmospheric turbulence

Pieter Piscaer; Lukas Knobel; Lotte Nijskens; Michel van Lier; Judith Dijk; Nicolas Boehrer

doi:10.1117/12.3031801

13 November 2024 Improving automatic text recognition through atmospheric turbulence

Pieter Piscaer, Lukas Knobel, Lotte Nijskens, Michel van Lier, Judith Dijk, Nicolas Boehrer

Author Affiliations +

Proceedings Volume 13206, Artificial Intelligence for Security and Defence Applications II; 1320610 (2024) https://doi.org/10.1117/12.3031801
Event: Security + Defence, 2024, Edinburgh, United Kingdom

Abstract

Image quality degradation caused by atmospheric turbulence reduces the performance of automated tasks such as optical character recognition. This issue is addressed by fine-tuning text recognition models using turbulencedegraded images. As obtaining a realistic training dataset of turbulence-degraded recordings is challenging, two synthetic datasets were created: one using a physics-inspired deep learning turbulence simulator and one using a heat chamber. The fine-tuned text recognition model leads to improved performance on a validation dataset of turbulence-distorted recordings. A number of architectural modifications to the text recognition model are proposed that allow for using a sequence of frames instead of just a single frame, while still using the pre-trained weights. These modifications are shown to lead to a further performance improvement.

Citation Download Citation

Pieter Piscaer, Lukas Knobel, Lotte Nijskens, Michel van Lier, Judith Dijk, and Nicolas Boehrer "Improving automatic text recognition through atmospheric turbulence", Proc. SPIE 13206, Artificial Intelligence for Security and Defence Applications II, 1320610 (13 November 2024); https://doi.org/10.1117/12.3031801

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