开发用于识别字体和大小无关的文本的商业级泰米尔OCR

2015 Fifteenth International Conference on Advances in ICT for Emerging Regions (ICTer) Pub Date : 2015-08-01 DOI:10.1109/ICTER.2015.7377678

Chamila Liyanage, Thilini Nadungodage, R. Weerasinghe

{"title":"开发用于识别字体和大小无关的文本的商业级泰米尔OCR","authors":"Chamila Liyanage, Thilini Nadungodage, R. Weerasinghe","doi":"10.1109/ICTER.2015.7377678","DOIUrl":null,"url":null,"abstract":"Optical Character Recognition (OCR) of Indic scripts such as Tamil and Sinhala has lagged behind those for languages based on the Latin script. Several attempts to build commercial grade OCR for these languages have failed in the past owing to them not generalizing well. This paper describes a set of training regimes for Tamil using the Tesseract engine that have enabled us to develop a robust Tamil OCR system. We describe in detail our training regime, which results in a performance improvement of 12.5% over the default Tamil module shipped with Tesseract on a set of ancient Tamil documents, which were part of an authentic project to digitize important Tamil manuscripts of Sri Lanka.","PeriodicalId":142561,"journal":{"name":"2015 Fifteenth International Conference on Advances in ICT for Emerging Regions (ICTer)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2015-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"10","resultStr":"{\"title\":\"Developing a commercial grade Tamil OCR for recognizing font and size independent text\",\"authors\":\"Chamila Liyanage, Thilini Nadungodage, R. Weerasinghe\",\"doi\":\"10.1109/ICTER.2015.7377678\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Optical Character Recognition (OCR) of Indic scripts such as Tamil and Sinhala has lagged behind those for languages based on the Latin script. Several attempts to build commercial grade OCR for these languages have failed in the past owing to them not generalizing well. This paper describes a set of training regimes for Tamil using the Tesseract engine that have enabled us to develop a robust Tamil OCR system. We describe in detail our training regime, which results in a performance improvement of 12.5% over the default Tamil module shipped with Tesseract on a set of ancient Tamil documents, which were part of an authentic project to digitize important Tamil manuscripts of Sri Lanka.\",\"PeriodicalId\":142561,\"journal\":{\"name\":\"2015 Fifteenth International Conference on Advances in ICT for Emerging Regions (ICTer)\",\"volume\":\"24 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2015-08-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"10\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2015 Fifteenth International Conference on Advances in ICT for Emerging Regions (ICTer)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICTER.2015.7377678\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2015 Fifteenth International Conference on Advances in ICT for Emerging Regions (ICTer)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICTER.2015.7377678","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 10

摘要

印度文字(如泰米尔语和僧伽罗语)的光学字符识别(OCR)落后于基于拉丁文字的语言。由于没有很好地泛化，过去为这些语言构建商业级OCR的几次尝试都失败了。本文描述了一组使用Tesseract引擎的泰米尔语训练机制，它使我们能够开发一个健壮的泰米尔语OCR系统。我们详细描述了我们的培训制度，这使得在一组古代泰米尔文件上，与Tesseract附带的默认泰米尔模块相比，性能提高了12.5%，这些文件是将斯里兰卡重要泰米尔手稿数字化的真实项目的一部分。

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

Developing a commercial grade Tamil OCR for recognizing font and size independent text

Optical Character Recognition (OCR) of Indic scripts such as Tamil and Sinhala has lagged behind those for languages based on the Latin script. Several attempts to build commercial grade OCR for these languages have failed in the past owing to them not generalizing well. This paper describes a set of training regimes for Tamil using the Tesseract engine that have enabled us to develop a robust Tamil OCR system. We describe in detail our training regime, which results in a performance improvement of 12.5% over the default Tamil module shipped with Tesseract on a set of ancient Tamil documents, which were part of an authentic project to digitize important Tamil manuscripts of Sri Lanka.

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

2015 Fifteenth International Conference on Advances in ICT for Emerging Regions (ICTer)

自引率

0.00%

发文量