1. Identity statement | |
Reference Type | Conference Paper (Conference Proceedings) |
Site | sibgrapi.sid.inpe.br |
Identifier | 8JMKD3MGPEW34M/47M827H |
Repository | sid.inpe.br/sibgrapi/2022/09.24.16.19 |
Last Update | 2022:09.24.16.23.08 (UTC) rblsantos@inf.ufpr.br |
Metadata Repository | sid.inpe.br/sibgrapi/2022/09.24.16.19.05 |
Metadata Last Update | 2023:05.23.04.20.43 (UTC) administrator |
DOI | 10.1109/SIBGRAPI55357.2022.9991768 |
Citation Key | LarocaSanEstLuzMen:2022:FiLoDa |
Title | A First Look at Dataset Bias in License Plate Recognition |
Format | On-line |
Year | 2022 |
Access Date | 2024, Apr. 29 |
Number of Files | 1 |
Size | 1944 KiB |
|
2. Context | |
Author | 1 Laroca, Rayson 2 Santos, Marcelo 3 Estevam, Valter 4 Luz, Eduardo 5 Menotti, David |
Affiliation | 1 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 Address | rblsantos@inf.ufpr.br |
Conference Name | Conference on Graphics, Patterns and Images, 35 (SIBGRAPI) |
Conference Location | Natal, RN |
Date | 24-27 Oct. 2022 |
Book Title | Proceedings |
Tertiary Type | Full 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 Stage | completed |
Transferable | 1 |
Keywords | license plate recognition dataset bias |
Abstract | Public 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. |
Arrangement | urlib.net > SDLA > Fonds > SIBGRAPI 2022 > A First Look... |
doc Directory Content | access |
source Directory Content | there are no files |
agreement Directory Content | |
|
4. Conditions of access and use | |
data URL | http://urlib.net/ibi/8JMKD3MGPEW34M/47M827H |
zipped data URL | http://urlib.net/zip/8JMKD3MGPEW34M/47M827H |
Language | en |
Target File | laroca2022first-inpe.pdf |
User Group | rblsantos@inf.ufpr.br |
Visibility | shown |
|
5. Allied materials | |
Mirror Repository | sid.inpe.br/banon/2001/03.30.15.38.24 |
Next Higher Units | 8JMKD3MGPEW34M/495MHJ8 |
Citing Item List | sid.inpe.br/sibgrapi/2023/05.19.12.10 5 |
Host Collection | sid.inpe.br/banon/2001/03.30.15.38 |
|
6. Notes | |
Empty Fields | archivingpolicy 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 |
|