Threshold U-Net: speed up document binarization with adaptive thresholds

Konstantin E. Lihota; Alexander V. Gayer; Vladimir V. Arlazarov

doi:10.1117/12.3023176

3 April 2024 Threshold U-Net: speed up document binarization with adaptive thresholds

Konstantin E. Lihota, Alexander V. Gayer, Vladimir V. Arlazarov

Proceedings Volume 13072, Sixteenth International Conference on Machine Vision (ICMV 2023); 130720T (2024) https://doi.org/10.1117/12.3023176
Event: Sixteenth International Conference on Machine Vision (ICMV 2023), 2023, Yerevan, Armenia

Abstract

U-Net similar architectures are widely used in the task of document image binarization. However, despite the good quality of binarization, they also have high computational complexity, which greatly limits their use on mobile and embedded devices. The performance bottleneck of U-Net architectures is the first encoder layers and the last decoder layers, which operate on high-resolution input data and contain the largest number of operations. Based on this, in this paper we propose a new Threshold U-Net model: instead of predicting the final image, Threshold U-Net predicts a low-resolution adaptive threshold map, with which the input image is binarized. The proposed architecture naturally combines the ideas of classical algorithms that calculate the binarization threshold for a specific image region with an approach based on a deep learning model with a large receptive field and context understanding. Threshold U-Net demonstrates quality of binarization of historical documents comparable to U-Net on the DIBCO-2017 dataset. At the same time, depending on the resolution of the threshold map, Threshold U-Net is up to 2 times faster, requires up to 26% less RAM and consists up to 10% fewer parameters.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Konstantin E. Lihota, Alexander V. Gayer, and Vladimir V. Arlazarov "Threshold U-Net: speed up document binarization with adaptive thresholds", Proc. SPIE 13072, Sixteenth International Conference on Machine Vision (ICMV 2023), 130720T (3 April 2024); https://doi.org/10.1117/12.3023176

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

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
8 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Image processing

Image quality

Neural networks

Deep learning

Mobile devices

Image segmentation

Neurons

Show All Keywords

Keywords/Phrases

Search In:

Publication Years