Repository logo

Infoscience

  • English
  • French
Log In
Logo EPFL, École polytechnique fédérale de Lausanne

Infoscience

  • English
  • French
Log In
  1. Home
  2. Academic and Research Output
  3. Conferences, Workshops, Symposiums, and Seminars
  4. dhSegment: A generic deep-learning approach for document segmentation
 
Loading...
Thumbnail Image
conference paper

dhSegment: A generic deep-learning approach for document segmentation

Oliveira, Sofia Ares  
•
Seguin, Benoit  
•
Kaplan, Frederic  
January 1, 2018
Proceedings 2018 16Th International Conference On Frontiers In Handwriting Recognition (Icfhr)
16th International Conference on Frontiers in Handwriting Recognition (ICFHR)

In recent years there have been multiple successful attempts tackling document processing problems separately by designing task specific hand-tuned strategies. We argue that the diversity of historical document processing tasks prohibits to solve them one at a time and shows a need for designing generic approaches in order to handle the variability of historical series. In this paper, we address multiple tasks simultaneously such as page extraction, baseline extraction, layout analysis or multiple typologies of illustrations and photograph extraction. We propose an open-source implementation of a CNN-based pixel-wise predictor coupled with task dependent post-processing blocks. We show that a single CNN-architecture can be used across tasks with competitive results. Moreover most of the task-specific post-precessing steps can be decomposed in a small number of simple and standard reusable operations, adding to the flexibility of our approach.

  • Details
  • Metrics
Type
conference paper
DOI
10.1109/ICFHR-2018.2018.00011
Web of Science ID

WOS:000454983200002

Author(s)
Oliveira, Sofia Ares  
•
Seguin, Benoit  
•
Kaplan, Frederic  
Date Issued

2018-01-01

Publisher

IEEE

Publisher place

New York

Published in
Proceedings 2018 16Th International Conference On Frontiers In Handwriting Recognition (Icfhr)
ISBN of the book

978-1-5386-5875-8

Series title/Series vol.

International Conference on Handwriting Recognition

Start page

7

End page

12

Subjects

Computer Science, Artificial Intelligence

•

Computer Science, Information Systems

•

Computer Science

•

document segmentation

•

historical document processing

•

document layout analysis

•

neural network

•

deep learning

Peer reviewed

REVIEWED

Written at

EPFL

EPFL units
DHLAB  
Event nameEvent placeEvent date
16th International Conference on Frontiers in Handwriting Recognition (ICFHR)

Niagara Falls, NY

Aug 05-08, 2018

Available on Infoscience
January 23, 2019
Use this identifier to reference this record
https://infoscience.epfl.ch/handle/20.500.14299/153778
Logo EPFL, École polytechnique fédérale de Lausanne
  • Contact
  • infoscience@epfl.ch

  • Follow us on Facebook
  • Follow us on Instagram
  • Follow us on LinkedIn
  • Follow us on X
  • Follow us on Youtube
AccessibilityLegal noticePrivacy policyCookie settingsEnd User AgreementGet helpFeedback

Infoscience is a service managed and provided by the Library and IT Services of EPFL. © EPFL, tous droits réservés