Identity statement area
Reference TypeConference Proceedings
Last Update2018:
Metadata Last Update2020: administrator
Citation KeyKuboNazAguOliDua:2018:UsUNPr
TitleThe usage of U-Net for pre-processing document images
DateOct. 29 - Nov. 1, 2018
Access Date2020, Dec. 04
Number of Files1
Size906 KiB
Context area
Author1 Kubo, Diandra Akemi
2 Nazare, Tiago Santana de
3 Aguirre, Priscila Louise Ribeiro
4 Oliveira, Bruno Domingues
5 Duarte, Felipe Simões Lage Gomes
Affiliation1 Data Science Team - Itau Unibanco
2 Data Science Team - Itau Unibanco
3 Data Science Team - Itau Unibanco
4 Data Science Team - Itau Unibanco
5 Data Science Team - Itau Unibanco
EditorRoss, Arun
Gastal, Eduardo S. L.
Jorge, Joaquim A.
Queiroz, Ricardo L. de
Minetto, Rodrigo
Sarkar, Sudeep
Papa, João Paulo
Oliveira, Manuel M.
Arbeláez, Pablo
Mery, Domingo
Oliveira, Maria Cristina Ferreira de
Spina, Thiago Vallin
Mendes, Caroline Mazetto
Costa, Henrique Sérgio Gutierrez
Mejail, Marta Estela
Geus, Klaus de
Scheer, Sergio
Conference NameConference on Graphics, Patterns and Images, 31 (SIBGRAPI)
Conference LocationFoz do Iguaçu, PR, Brazil
Book TitleProceedings
PublisherSociedade Brasileira de Computação
Publisher CityPorto Alegre
History2018-10-24 00:46:42 :: -> administrator ::
2020-02-20 22:06:51 :: administrator -> :: 2018
Content and structure area
Is the master or a copy?is the master
Document Stagecompleted
Document Stagenot transferred
Tertiary TypeIndustry Application Paper
Keywords#deep-learning #computer-vision #image-processing.
AbstractWhen processing documents in real-world scenarios, it is common to deal with artifacts that may hamper document analysis, such as stamps, noise and strange backgrounds. Aiming to mitigate these problems, we propose the use of U-Net, a very successful biomedical image segmentation network, for handwritten and machine text segmentation. In order to do so, we trained a model for each type of text. One of the main advantages presented is that the models are trained on artificial data, avoiding the wearisome task of data labeling. For the machine text segmentation model, we test its impacts on both word and character recognition when combined with the Tesseract OCR model. For the handwritten segmentation model, we present qualitative results. Initial experiments indicate that both models are able to improve results in their respective applications.
source Directory Contentthere are no files
agreement Directory Content
agreement.html 23/10/2018 21:46 1.2 KiB 
Conditions of access and use area
Target Filesibgrapi_pi_cv.pdf
Allied materials area
Next Higher Units8JMKD3MGPAW/3RPADUS
Notes area
Empty Fieldsaccessionnumber archivingpolicy archivist area callnumber contenttype 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