dhSegment: A generic deep-learning approach for document segmentation

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 We argue that the diversity of historical document processing tasks prohibits to solve them one at a time and shows a need for designing generic approaches in order to handle the variability of historical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.


Published in:
Proceedings 2018 16Th International Conference On Frontiers In Handwriting Recognition (Icfhr), 7-12
Presented at:
16th International Conference on Frontiers in Handwriting Recognition (ICFHR), Niagara Falls, NY, Aug 05-08, 2018
Year:
Jan 01 2018
Publisher:
New York, IEEE
ISSN:
2167-6445
ISBN:
978-1-5386-5875-8
Keywords:
Laboratories:




 Record created 2019-01-23, last modified 2020-04-16


Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)