Close
Metadata

1. Identity statement
Reference TypeConference Paper (Conference Proceedings)
Sitesibgrapi.sid.inpe.br
Identifier8JMKD3MGPEW34M/47M827H
Repositorysid.inpe.br/sibgrapi/2022/09.24.16.19
Last Update2022:09.24.16.23.08 (UTC) rblsantos@inf.ufpr.br
Metadata Repositorysid.inpe.br/sibgrapi/2022/09.24.16.19.05
Metadata Last Update2023:05.23.04.20.43 (UTC) administrator
DOI10.1109/SIBGRAPI55357.2022.9991768
Citation KeyLarocaSanEstLuzMen:2022:FiLoDa
TitleA First Look at Dataset Bias in License Plate Recognition
FormatOn-line
Year2022
Access Date2024, Apr. 29
Number of Files1
Size1944 KiB
2. Context
Author1 Laroca, Rayson
2 Santos, Marcelo
3 Estevam, Valter
4 Luz, Eduardo
5 Menotti, David
Affiliation1 Federal University of Paraná
2 Federal University of Paraná
3 Federal University of Paraná
4 Federal University of Ouro Preto
5 Federal University of Paraná
e-Mail Addressrblsantos@inf.ufpr.br
Conference NameConference on Graphics, Patterns and Images, 35 (SIBGRAPI)
Conference LocationNatal, RN
Date24-27 Oct. 2022
Book TitleProceedings
Tertiary TypeFull Paper
History (UTC)2022-09-24 16:23:08 :: rblsantos@inf.ufpr.br -> administrator :: 2022
2023-05-23 04:20:43 :: administrator -> :: 2022
3. Content and structure
Is the master or a copy?is the master
Content Stagecompleted
Transferable1
Keywordslicense plate recognition
dataset bias
AbstractPublic datasets have played a key role in advancing the state of the art in License Plate Recognition (LPR). Although dataset bias has been recognized as a severe problem in the computer vision community, it has been largely overlooked in the LPR literature. LPR models are usually trained and evaluated separately on each dataset. In this scenario, they have often proven robust in the dataset they were trained in but showed limited performance in unseen ones. Therefore, this work investigates the dataset bias problem in the LPR context. We performed experiments on eight datasets, four collected in Brazil and four in mainland China, and observed that each dataset has a unique, identifiable "signature" since a lightweight classification model predicts the source dataset of a license plate (LP) image with more than 95% accuracy. In our discussion, we draw attention to the fact that most LPR models are probably exploiting such signatures to improve the results achieved in each dataset at the cost of losing generalization capability. These results emphasize the importance of evaluating LPR models in cross-dataset setups, as they provide a better indication of generalization (hence real-world performance) than within-dataset ones.
Arrangementurlib.net > SDLA > Fonds > SIBGRAPI 2022 > A First Look...
doc Directory Contentaccess
source Directory Contentthere are no files
agreement Directory Content
agreement.html 24/09/2022 13:19 1.6 KiB 
4. Conditions of access and use
data URLhttp://urlib.net/ibi/8JMKD3MGPEW34M/47M827H
zipped data URLhttp://urlib.net/zip/8JMKD3MGPEW34M/47M827H
Languageen
Target Filelaroca2022first-inpe.pdf
User Grouprblsantos@inf.ufpr.br
Visibilityshown
5. Allied materials
Mirror Repositorysid.inpe.br/banon/2001/03.30.15.38.24
Next Higher Units8JMKD3MGPEW34M/495MHJ8
Citing Item Listsid.inpe.br/sibgrapi/2023/05.19.12.10 5
Host Collectionsid.inpe.br/banon/2001/03.30.15.38
6. Notes
Empty Fieldsarchivingpolicy archivist area callnumber contenttype copyholder copyright creatorhistory descriptionlevel dissemination documentstage edition editor electronicmailaddress group holdercode isbn issn label lineage mark nextedition notes numberofvolumes orcid organization pages parameterlist parentrepositories previousedition previouslowerunit progress project publisher publisheraddress readergroup readpermission resumeid rightsholder schedulinginformation secondarydate secondarykey secondarymark secondarytype serieseditor session shorttitle sponsor subject tertiarymark type url versiontype volume


Close