ICDAR2017基于COCO-Text的稳健阅读挑战

2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR) Pub Date : 2017-11-01 DOI:10.1109/ICDAR.2017.234

Raul Gomez, Baoguang Shi, L. G. I. Bigorda, Lukás Neumann, Andreas Veit, Jiri Matas, Serge J. Belongie, Dimosthenis Karatzas

{"title":"ICDAR2017基于COCO-Text的稳健阅读挑战","authors":"Raul Gomez, Baoguang Shi, L. G. I. Bigorda, Lukás Neumann, Andreas Veit, Jiri Matas, Serge J. Belongie, Dimosthenis Karatzas","doi":"10.1109/ICDAR.2017.234","DOIUrl":null,"url":null,"abstract":"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.","PeriodicalId":433676,"journal":{"name":"2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"45","resultStr":"{\"title\":\"ICDAR2017 Robust Reading Challenge on COCO-Text\",\"authors\":\"Raul Gomez, Baoguang Shi, L. G. I. Bigorda, Lukás Neumann, Andreas Veit, Jiri Matas, Serge J. Belongie, Dimosthenis Karatzas\",\"doi\":\"10.1109/ICDAR.2017.234\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"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.\",\"PeriodicalId\":433676,\"journal\":{\"name\":\"2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR)\",\"volume\":\"7 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2017-11-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"45\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICDAR.2017.234\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICDAR.2017.234","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 45

摘要

本报告介绍了ICDAR 2017年COCO-Text稳健阅读挑战的最终结果。基于目前可用的最大真实场景文本数据集:COCO-Text数据集，对场景文本检测和识别的挑战。比赛围绕三个任务展开:文本定位、裁剪词识别和端到端识别。比赛共收到了27份不同开放任务的参赛作品。本报告描述了数据集和基本事实，详细介绍了所使用的性能评估协议，并介绍了最终结果以及参与方法的简要摘要。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

ICDAR2017 Robust Reading Challenge on COCO-Text

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.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR)

自引率

0.00%

发文量