Please use this identifier to cite or link to this item:
http://hdl.handle.net/10553/107487
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Das, Abhijit | en_US |
dc.contributor.author | Ferrer, Miguel A. | en_US |
dc.contributor.author | Morales Moreno, Aythami | en_US |
dc.contributor.author | Díaz Cabrera, Moisés | en_US |
dc.contributor.author | Pal, Umapada | en_US |
dc.contributor.author | Impedovo, Donato | en_US |
dc.contributor.author | Hongliang Li | en_US |
dc.contributor.author | Wentao Yang | en_US |
dc.contributor.author | Kensho Ota | en_US |
dc.contributor.author | Tadahito Yao | en_US |
dc.contributor.author | Le Quang Hung | en_US |
dc.contributor.author | Nguyen Quoc Cuong | en_US |
dc.contributor.author | Seungjae Kim | en_US |
dc.contributor.author | Gattal, Abdeljalil | en_US |
dc.date.accessioned | 2021-06-11T11:31:38Z | - |
dc.date.available | 2021-06-11T11:31:38Z | - |
dc.date.issued | 2021 | en_US |
dc.identifier.uri | http://hdl.handle.net/10553/107487 | - |
dc.description.abstract | The paper presents a summary of the 1st Competition on Script Identification in the Wild (SIW 2021) organised in conjunction with 16th International Conference on Document Analysis and Recognition (ICDAR 2021). The goal of SIW is to evaluate the limits of script identification approaches through a large scale in the wild database including 13 scripts (MDIW-13 dataset) and two different scenarios (handwritten and printed). The competition includes the evaluation over three different tasks depending of the nature of the data used for training and testing. Nineteen research groups registered for SIW 2021, out of which 6 teams from both academia and industry took part in the final round and submitted a total of 166 algorithms for scoring. Submissions included a wide variety of deep-learning solutions as well as approaches based on standard image processing techniques. The performance achieved by the participants prove the elevate accuracy of deep learning methods in comparison with traditional statistical approaches. The best approach obtained classification accuracies of 99% in all three tasks with experiments over more than 50K test samples. The results suggest that there is still room for improvements, specially over handwritten samples and specific scripts. | en_US |
dc.language | eng | en_US |
dc.publisher | Springer | en_US |
dc.source | Document Analysis and Recognition – ICDAR 2021 / Josep Lladós, Prof. Daniel Lopresti, Seiichi Uchida (eds.), v. IV | en_US |
dc.subject | 2405 Biometría | en_US |
dc.subject | 570102 Documentación automatizada | en_US |
dc.subject.other | Handwritten and printed script identification | en_US |
dc.subject.other | Wild | en_US |
dc.subject.other | Deep learning | en_US |
dc.subject.other | Multi-script | en_US |
dc.title | SIW 2021: ICDAR Competition on Script Identification in the Wild | en_US |
dc.type | info:eu-repo/semantics/conferenceobject | en_US |
dc.type | ConferenceObject | en_US |
dc.relation.conference | 16th International Conference on Document Analysis and Recognition (ICDAR 2021) | en_US |
dc.investigacion | Ingeniería y Arquitectura | en_US |
dc.type2 | Actas de congresos | en_US |
dc.description.numberofpages | 17 | en_US |
dc.utils.revision | Sí | en_US |
dc.identifier.ulpgc | Sí | en_US |
dc.contributor.buulpgc | BU-BAS | en_US |
dc.description.ggs | 2 | |
item.fulltext | Con texto completo | - |
item.grantfulltext | open | - |
crisitem.event.eventsstartdate | 05-09-2021 | - |
crisitem.event.eventsenddate | 10-09-2021 | - |
crisitem.author.dept | GIR IDeTIC: División de Procesado Digital de Señales | - |
crisitem.author.dept | IU para el Desarrollo Tecnológico y la Innovación | - |
crisitem.author.dept | Departamento de Señales y Comunicaciones | - |
crisitem.author.dept | GIR IDeTIC: División de Procesado Digital de Señales | - |
crisitem.author.dept | IU para el Desarrollo Tecnológico y la Innovación | - |
crisitem.author.dept | Departamento de Física | - |
crisitem.author.orcid | 0000-0002-2924-1225 | - |
crisitem.author.orcid | 0000-0003-3878-3867 | - |
crisitem.author.parentorg | IU para el Desarrollo Tecnológico y la Innovación | - |
crisitem.author.parentorg | IU para el Desarrollo Tecnológico y la Innovación | - |
crisitem.author.fullName | Ferrer Ballester, Miguel Ángel | - |
crisitem.author.fullName | Morales Moreno,Aythami | - |
crisitem.author.fullName | Díaz Cabrera, Moisés | - |
Appears in Collections: | Actas de congresos |
Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.