ICDAR2017 Robust Reading Challenge on COCO-Text
Publikation: Bidrag til tidsskrift › Konferenceartikel › Forskning › fagfællebedømt
This report presents the final results of the ICDAR 2017 Robust Reading Challenge on COCO-Text. A challenge on scene text detection and recognition based on the largest real scene text dataset currently available: the COCO-Text dataset. The competition is structured around three tasks: Text Localization, Cropped Word Recognition and End-To-End Recognition. The competition received a total of 27 submissions over the different opened tasks. This report describes the datasets and the ground truth, details the performance evaluation protocols used and presents the final results along with a brief summary of the participating methods.
Originalsprog | Engelsk |
---|---|
Tidsskrift | Proceedings of the International Conference on Document Analysis and Recognition, ICDAR |
Sider (fra-til) | 1435-1443 |
Antal sider | 9 |
ISSN | 1520-5363 |
DOI | |
Status | Udgivet - 25 jan. 2018 |
Eksternt udgivet | Ja |
Begivenhed | 14th IAPR International Conference on Document Analysis and Recognition, ICDAR 2017 - Kyoto, Japan Varighed: 9 nov. 2017 → 15 nov. 2017 |
Konference
Konference | 14th IAPR International Conference on Document Analysis and Recognition, ICDAR 2017 |
---|---|
Land | Japan |
By | Kyoto |
Periode | 09/11/2017 → 15/11/2017 |
Sponsor | et al., FxPaL, Glory, Hitachi, Media Drive, Sansan |
Bibliografisk note
Publisher Copyright:
© 2017 IEEE.
ID: 301826271