Close
Metadata

Identity statement area
Reference TypeConference Proceedings
Sitesibgrapi.sid.inpe.br
Identifier8JMKD3MGPEW34M/4388QM2
Repositorysid.inpe.br/sibgrapi/2020/09.10.14.33
Last Update2020:10.01.19.49.53 byron.leite@upe.br
Metadatasid.inpe.br/sibgrapi/2020/09.10.14.33.12
Metadata Last Update2020:10.28.20.46.46 administrator
Citation KeySouzaNetoBezeToseLima:2020:DeLeSy
TitleHTR-Flor: a deep learning system for offline handwritten text recognition
FormatOn-line
Year2020
DateNov. 7-10, 2020
Access Date2020, Dec. 04
Number of Files1
Size957 KiB
Context area
Author1 Souza Neto, Arthur Flor de
2 Bezerra, Byron Leite Dantas
3 Toselli, Alejandro Hector
4 Lima, Estanislau Baptista
Affiliation1 Universidade de Pernambuco
2 Universidade de Pernambuco
3 Universitat Politecnica de Valencia
4 Universidade de Pernambuco
EditorMusse, Soraia Raupp
Cesar Junior, Roberto Marcondes
Pelechano, Nuria
Wang, Zhangyang (Atlas)
e-Mail Addressbyron.leite@upe.br
Conference NameConference on Graphics, Patterns and Images, 33 (SIBGRAPI)
Conference LocationVirtual
Book TitleProceedings
PublisherIEEE Computer Society
Publisher CityLos Alamitos
History2020-10-01 19:49:54 :: byron.leite@upe.br -> administrator :: 2020
2020-10-28 20:46:46 :: administrator -> byron.leite@upe.br :: 2020
Content and structure area
Is the master or a copy?is the master
Document Stagecompleted
Document Stagenot transferred
Transferable1
Content TypeExternal Contribution
Tertiary TypeFull Paper
KeywordsHandwritten Text Recognition, Gated Convolutional Neural Networks, Gated CNN, Deep Neural Networks.
AbstractIn recent years, Handwritten Text Recognition (HTR) has captured a lot of attention among the researchers of the computer vision community. Current state-of-the-art approaches for offline HTR are based on Convolutional Recurrent Neural Networks (CRNNs) excel at scene text recognition. Unfortunately, deep models such as CRNNs, Recurrent Neural Networks (RNNs) are likely to suffer from vanishing/exploding gradient problems when processing long text images, which are commonly found in scanned documents. Besides, they usually have millions of parameters which require huge amount of data, and computational resource. Recently, a new class of neural network architecture, called Gated Convolutional Neural Networks (Gated-CNN), has demonstrated potentials to complement CRNN methods in modeling. Therefore, in this paper, we present a new architecture for HTR, based on Gated-CNN, with fewer parameters and fewer layers, which is able to outperform the current state-of-the-art architectures for HTR. The experiment validates that the proposed model has statistically significant recognition results, surpassing previous HTR systems by an average of 33% over five important handwritten benchmark datasets. Moreover, the proposed model is able to achieve satisfactory recognition rates even in case of few training data. Finally, its compact architecture requires less computational resources, which can be applied for real-world applications that have hardware limitations, such as robots and smartphones.
source Directory Content
PID6607213.pdf 10/09/2020 11:33 956.6 KiB 
agreement Directory Content
agreement.html 10/09/2020 11:33 1.2 KiB 
Conditions of access and use area
Languageen
Target FilePID6607213.pdf
e-Mail (login)byron.leite@upe.br
User Groupbyron.leite@upe.br
Visibilityshown
Allied materials area
Mirror Repositorysid.inpe.br/banon/2001/03.30.15.38.24
Next Higher Units8JMKD3MGPEW34M/43G4L9S
Host Collectionsid.inpe.br/banon/2001/03.30.15.38
Notes area
Empty Fieldsaccessionnumber archivingpolicy archivist area callnumber copyholder copyright creatorhistory descriptionlevel dissemination doi edition electronicmailaddress group holdercode isbn issn label lineage mark nextedition notes numberofvolumes orcid organization pages parameterlist parentrepositories previousedition previouslowerunit progress project readergroup readpermission resumeid rightsholder secondarydate secondarykey secondarymark secondarytype serieseditor session shorttitle sponsor subject tertiarymark type url versiontype volume
Description control area
update 

Close