{"title":"Automatic Thai and English fonts identification without character recognition","authors":"B. Kruatrachue, Pongsakorn Piyatrakul","doi":"10.1109/PACRIM.2001.953705","DOIUrl":null,"url":null,"abstract":"This paper describes a simple and fast algorithm to detect Thai and English characters in a document without doing actual characters recognition. The document is segmented into strings of letters separated by a blank, then each string is identified using characters features and their writing positions. This method achieves 100% accuracy if the characters have clear head feature. But if this feature is not used 90% of the strings still can be identified. This identification provides more information about the character set so that OCR can recognize faster with better accuracy.","PeriodicalId":261724,"journal":{"name":"2001 IEEE Pacific Rim Conference on Communications, Computers and Signal Processing (IEEE Cat. No.01CH37233)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2001-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2001 IEEE Pacific Rim Conference on Communications, Computers and Signal Processing (IEEE Cat. No.01CH37233)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/PACRIM.2001.953705","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 3
Abstract
This paper describes a simple and fast algorithm to detect Thai and English characters in a document without doing actual characters recognition. The document is segmented into strings of letters separated by a blank, then each string is identified using characters features and their writing positions. This method achieves 100% accuracy if the characters have clear head feature. But if this feature is not used 90% of the strings still can be identified. This identification provides more information about the character set so that OCR can recognize faster with better accuracy.