Publication Details

Towards Writing Style Adaptation in Handwriting Recognition

KOHÚT, J.; HRADIŠ, M.; KIŠŠ, M. Towards Writing Style Adaptation in Handwriting Recognition. In Document Analysis and Recognition - ICDAR 2023. Lecture Notes in Computer Science. Lecture Notes in Computer Science. San José: Springer Nature Switzerland AG, 2023. p. 377-394. ISBN: 978-3-031-41684-2. ISSN: 0302-9743.
Czech title
Adaptace na styl písma v rámci rozpoznávání ručně psaného textu
Type
conference paper
Language
English
Authors
URL
Keywords

Handwritten text recognition, OCR, Domain adaptation, Domain dependent
parameters, Finetuning, CTC.

Abstract

One of the challenges of handwriting recognition is to transcribe a large number
of vastly different writing styles. State-of-the-art approaches do not explicitly
use information about the writer's style, which may be limiting overall accuracy
due to various ambiguities. We explore models with writer-dependent parameters
which take the writer's identity as an additional input. The proposed models can
be trained on datasets with partitions likely written by a single author (e.g.
single letter, diary, or chronicle). We propose a Writer Style Block (WSB), an
adaptive instance normalization layer conditioned on learned embeddings of the
partitions. We experimented with various placements and settings of WSB and
contrastively pre-trained embeddings. We show that our approach outperforms
a baseline with no WSB in a writer-dependent scenario and that it is possible to
estimate embeddings for new writers. However, domain adaptation using simple
finetuning in a writer-independent setting provides superior accuracy at
a similar computational cost. The proposed approach should be further
investigated in terms of training stability and embedding regularization to
overcome such a baseline.

Published
2023
Pages
377–394
Journal
Lecture Notes in Computer Science, vol. 14190, no. 1, ISSN 0302-9743
Proceedings
Document Analysis and Recognition - ICDAR 2023
Series
Lecture Notes in Computer Science
Conference
International Conference on Document Analysis and Recognition, San José, California, USA, US
ISBN
978-3-031-41684-2
Publisher
Springer Nature Switzerland AG
Place
San José
DOI
EID Scopus
BibTeX
@inproceedings{BUT185150,
  author="Jan {Kohút} and Michal {Hradiš} and Martin {Kišš}",
  title="Towards Writing Style Adaptation in Handwriting Recognition",
  booktitle="Document Analysis and Recognition - ICDAR 2023",
  year="2023",
  series="Lecture Notes in Computer Science",
  journal="Lecture Notes in Computer Science",
  volume="14190",
  number="1",
  pages="377--394",
  publisher="Springer Nature Switzerland AG",
  address="San José",
  doi="10.1007/978-3-031-41685-9\{_}24",
  isbn="978-3-031-41684-2",
  issn="0302-9743",
  url="https://pero.fit.vutbr.cz/publications"
}
Back to top