Publication detail

Page Layout Analysis System for Unconstrained Historic Documents

KODYM, O. HRADIŠ, M.

Original Title

Page Layout Analysis System for Unconstrained Historic Documents

Type

conference paper

Language

English

Original Abstract

Extraction of text regions and individual text lines from historic documents is necessary for automatic transcription. We propose extending a CNN-based text baseline detection system by adding line height and text block boundary predictions to the model output, allowing the system to extract more comprehensive layout information. We also show that pixel-wise text orientation prediction can be used for processing documents with multiple text orientations. We demonstrate that the proposed method performs well on the cBAD baseline detection dataset. Additionally, we benchmark the method on newly introduced PERO layout dataset which we also make public.

Keywords

Layout analysis, Historic documents analysis, Text line extraction 

Authors

KODYM, O.; HRADIŠ, M.

Released

2. 9. 2021

Publisher

Springer Nature Switzerland AG

Location

Lausanne

ISBN

978-3-030-86330-2

Book

Lladós J., Lopresti D., Uchida S. (eds) Document Analysis and Recognition - ICDAR 2021

Edition

Lecture Notes in Computer Science

Pages from

492

Pages to

506

Pages count

15

BibTex

@inproceedings{BUT175782,
  author="Oldřich {Kodym} and Michal {Hradiš}",
  title="Page Layout Analysis System for Unconstrained Historic Documents",
  booktitle="Lladós J., Lopresti D., Uchida S. (eds) Document Analysis and Recognition - ICDAR 2021",
  year="2021",
  series="Lecture Notes in Computer Science",
  pages="492--506",
  publisher="Springer Nature Switzerland AG",
  address="Lausanne",
  doi="10.1007/978-3-030-86331-9\{_}32",
  isbn="978-3-030-86330-2"
}