TS-Net: OCR Trained to Switch Between Text Transcription Styles
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F21%3APU139693" target="_blank" >RIV/00216305:26230/21:PU139693 - isvavai.cz</a>
Result on the web
<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/10.1007/978-3-030-86337-1_32" target="_blank" >10.1007/978-3-030-86337-1_32</a>
Alternative languages
Result language
angličtina
Original language name
TS-Net: OCR Trained to Switch Between Text Transcription Styles
Original language description
Multiple transcribers produce transcriptions in inconsistent transcription styles. This presents a problem for training consistent neural network systems for text recognition. We propose Transcription Style Block (TSB) which can learn to switch between multiple transcription styles without any explicit knowledge about the transcription rules. TSB is an adaptive instance normalization conditioned by transcription style identifiers e.g. document numbers or transcriber names and it can be added near the end of any standard text recognition network. We show that TSB is robust towards the number and complexity of transcription styles and does not degrade the text recognition performance. With time and data efficient adaptation to a new transcription style, we achieved up to 77% relative test character error reduction in comparison to a network without the TSB.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
<a href="/en/project/DG18P02OVV055" target="_blank" >DG18P02OVV055: Advanced content extraction and recognition for printed and handwritten documents for better accessibility and usability</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2021
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Lladós J., Lopresti D., Uchida S. (eds) Document Analysis and Recognition - ICDAR 2021
ISBN
978-3-030-86336-4
ISSN
0302-9743
e-ISSN
—
Number of pages
16
Pages from-to
478-493
Publisher name
Springer Nature Switzerland AG
Place of publication
Lausanne
Event location
Lausanne, Switzerland
Event date
Sep 5, 2021
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000711880100032