Towards Writing Style Adaptation in Handwriting Recognition

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F23%3APU149377" target="_blank" >RIV/00216305:26230/23:PU149377 - isvavai.cz</a>

Výsledek na webu

<a href="https://pero.fit.vutbr.cz/publications" target="_blank" >https://pero.fit.vutbr.cz/publications</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-031-41685-9_24" target="_blank" >10.1007/978-3-031-41685-9_24</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Towards Writing Style Adaptation in Handwriting Recognition

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

Towards Writing Style Adaptation in Handwriting Recognition

Popis výsledku anglicky

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.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2023

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Document Analysis and Recognition - ICDAR 2023

ISBN

978-3-031-41684-2

ISSN

0302-9743

e-ISSN

—

Počet stran výsledku

18

Strana od-do

377-394

Název nakladatele

Springer Nature Switzerland AG

Místo vydání

San José

Místo konání akce

San José, California, USA

Datum konání akce

21. 8. 2023

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—