Skip to Main Content (Press Enter)

Logo UNIMORE
  • ×
  • Home
  • Degree programmes
  • Modules
  • Jobs
  • People
  • Research Outputs
  • Academic units
  • Third Mission
  • Projects
  • Skills

UNI-FIND
Logo UNIMORE

|

UNI-FIND

unimore.it
  • ×
  • Home
  • Degree programmes
  • Modules
  • Jobs
  • People
  • Research Outputs
  • Academic units
  • Third Mission
  • Projects
  • Skills
  1. Research Outputs

Binarizing Documents by Leveraging both Space and Frequency

Conference Paper
Publication Date:
2024
Short description:
Binarizing Documents by Leveraging both Space and Frequency / Quattrini, F.; Pippi, V.; Cascianelli, S.; Cucchiara, R.. - 14806:(2024), pp. 3-22. ( 18th International Conference on Document Analysis and Recognition, ICDAR 2024 Athens, GREECE AUG 30-SEP 04, 2024) [10.1007/978-3-031-70543-4_1].
abstract:
Document Image Binarization is a well-known problem in Document Analysis and Computer Vision, although it is far from being solved. One of the main challenges of this task is that documents generally exhibit degradations and acquisition artifacts that can greatly vary throughout the page. Nonetheless, even when dealing with a local patch of the document, taking into account the overall appearance of a wide portion of the page can ease the prediction by enriching it with semantic information on the ink and background conditions. In this respect, approaches able to model both local and global information have been proven suitable for this task. In particular, recent applications of Vision Transformer (ViT)-based models, able to model short and long-range dependencies via the attention mechanism, have demonstrated their superiority over standard Convolution-based models, which instead struggle to model global dependencies. In this work, we propose an alternative solution based on the recently introduced Fast Fourier Convolutions, which overcomes the limitation of standard convolutions in modeling global information while requiring fewer parameters than ViTs. We validate the effectiveness of our approach via extensive experimental analysis considering different types of degradations.
Iris type:
Relazione in Atti di Convegno
Keywords:
Document Enhancement; Document Image Binarization; Fast Fourier Convolution
List of contributors:
Quattrini, F.; Pippi, V.; Cascianelli, S.; Cucchiara, R.
Authors of the University:
CASCIANELLI Silvia
CUCCHIARA Rita
Handle:
https://iris.unimore.it/handle/11380/1363929
Book title:
DOCUMENT ANALYSIS AND RECOGNITION-ICDAR 2024, PT III
Published in:
LECTURE NOTES IN COMPUTER SCIENCE
Journal
LECTURE NOTES IN COMPUTER SCIENCE
Series
  • Use of cookies

Powered by VIVO | Designed by Cineca | 26.4.5.0