HoughToRadon transform: new neural network layer for features improvement in projection space

Alexandra Zhabitskaya; Alexander Sheshkus; Vladimir L. Arlazarov

doi:10.1117/12.3023163

3 April 2024 HoughToRadon transform: new neural network layer for features improvement in projection space

Alexandra Zhabitskaya, Alexander Sheshkus, Vladimir L. Arlazarov

Proceedings Volume 13072, Sixteenth International Conference on Machine Vision (ICMV 2023); 1307210 (2024) https://doi.org/10.1117/12.3023163
Event: Sixteenth International Conference on Machine Vision (ICMV 2023), 2023, Yerevan, Armenia

Abstract

In this paper, we introduce HoughToRadon Transform layer, a novel layer designed to improve the speed of neural networks incorporated with Hough Transform to solve semantic image segmentation problems. By placing it after a Hough Transform layer, ’inner’ convolutions receive modified feature maps with new beneficial properties, such as a smaller area of processed images and parameter space linearity by angle and shift. These properties were not presented in Hough Transform alone. Furthermore, HoughToRadon Transform layer allows us to adjust the size of intermediate feature maps using two new parameters, thus allowing us to balance the speed and quality of the resulting neural network. Our experiments on the open MIDV-500 dataset show that this new approach leads to time savings in document segmentation tasks and achieves state-of-the-art 97.7% accuracy, outperforming HoughEncoder with larger computational complexity.

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

Citation Download Citation

Alexandra Zhabitskaya, Alexander Sheshkus, and Vladimir L. Arlazarov "HoughToRadon transform: new neural network layer for features improvement in projection space", Proc. SPIE 13072, Sixteenth International Conference on Machine Vision (ICMV 2023), 1307210 (3 April 2024); https://doi.org/10.1117/12.3023163

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

Neural networks

Hough transforms

Convolution

Image segmentation

Education and training

Semantics

Image processing

Keywords/Phrases

Search In:

Publication Years