HoughToRadon Transform: New Neural Network Layer for Features Improvement in Projection Space

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Zhabitskaya, Alexandra, Sheshkus, Alexander, Arlazarov, Vladimir L.
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914666834296832
author Zhabitskaya, Alexandra
Sheshkus, Alexander
Arlazarov, Vladimir L.
author_facet Zhabitskaya, Alexandra
Sheshkus, Alexander
Arlazarov, Vladimir L.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2402_02946
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle HoughToRadon Transform: New Neural Network Layer for Features Improvement in Projection Space
Zhabitskaya, Alexandra
Sheshkus, Alexander
Arlazarov, Vladimir L.
Computer Vision and Pattern Recognition
Machine Learning
Neural and Evolutionary Computing
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.
title HoughToRadon Transform: New Neural Network Layer for Features Improvement in Projection Space
topic Computer Vision and Pattern Recognition
Machine Learning
Neural and Evolutionary Computing
url https://arxiv.org/abs/2402.02946