@inproceedings{kitagawa-etal-2022-handwritten,
title = "Handwritten Character Generation using {Y}-Autoencoder for Character Recognition Model Training",
author = "Kitagawa, Tomoki and
Leow, Chee Siang and
Nishizaki, Hiromitsu",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.799",
pages = "7344--7351",
abstract = "It is well-known that the deep learning-based optical character recognition (OCR) system needs a large amount of data to train a high-performance character recognizer. However, it is costly to collect a large amount of realistic handwritten characters. This paper introduces a Y-Autoencoder (Y-AE)-based handwritten character generator to generate multiple Japanese Hiragana characters with a single image to increase the amount of data for training a handwritten character recognizer. The adaptive instance normalization (AdaIN) layer allows the generator to be trained and generate handwritten character images without paired-character image labels. The experiment shows that the Y-AE could generate Japanese character images then used to train the handwritten character recognizer, producing an F1-score improved from 0.8664 to 0.9281. We further analyzed the usefulness of the Y-AE-based generator with shape images, out-of-character (OOC) images, which have different character images styles in model training. The result showed that the generator could generate a handwritten image with a similar style to that of the input character.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kitagawa-etal-2022-handwritten">
<titleInfo>
<title>Handwritten Character Generation using Y-Autoencoder for Character Recognition Model Training</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tomoki</namePart>
<namePart type="family">Kitagawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chee</namePart>
<namePart type="given">Siang</namePart>
<namePart type="family">Leow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiromitsu</namePart>
<namePart type="family">Nishizaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>It is well-known that the deep learning-based optical character recognition (OCR) system needs a large amount of data to train a high-performance character recognizer. However, it is costly to collect a large amount of realistic handwritten characters. This paper introduces a Y-Autoencoder (Y-AE)-based handwritten character generator to generate multiple Japanese Hiragana characters with a single image to increase the amount of data for training a handwritten character recognizer. The adaptive instance normalization (AdaIN) layer allows the generator to be trained and generate handwritten character images without paired-character image labels. The experiment shows that the Y-AE could generate Japanese character images then used to train the handwritten character recognizer, producing an F1-score improved from 0.8664 to 0.9281. We further analyzed the usefulness of the Y-AE-based generator with shape images, out-of-character (OOC) images, which have different character images styles in model training. The result showed that the generator could generate a handwritten image with a similar style to that of the input character.</abstract>
<identifier type="citekey">kitagawa-etal-2022-handwritten</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.799</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>7344</start>
<end>7351</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Handwritten Character Generation using Y-Autoencoder for Character Recognition Model Training
%A Kitagawa, Tomoki
%A Leow, Chee Siang
%A Nishizaki, Hiromitsu
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F kitagawa-etal-2022-handwritten
%X It is well-known that the deep learning-based optical character recognition (OCR) system needs a large amount of data to train a high-performance character recognizer. However, it is costly to collect a large amount of realistic handwritten characters. This paper introduces a Y-Autoencoder (Y-AE)-based handwritten character generator to generate multiple Japanese Hiragana characters with a single image to increase the amount of data for training a handwritten character recognizer. The adaptive instance normalization (AdaIN) layer allows the generator to be trained and generate handwritten character images without paired-character image labels. The experiment shows that the Y-AE could generate Japanese character images then used to train the handwritten character recognizer, producing an F1-score improved from 0.8664 to 0.9281. We further analyzed the usefulness of the Y-AE-based generator with shape images, out-of-character (OOC) images, which have different character images styles in model training. The result showed that the generator could generate a handwritten image with a similar style to that of the input character.
%U https://aclanthology.org/2022.lrec-1.799
%P 7344-7351
Markdown (Informal)
[Handwritten Character Generation using Y-Autoencoder for Character Recognition Model Training](https://aclanthology.org/2022.lrec-1.799) (Kitagawa et al., LREC 2022)
ACL