首页> 外国专利> METHOD, A SYSTEM AND A COMPUTER-READABLE RECORDING MEDIUM FOR CORRECTING A RESULT OF OCR, PARTICULARLY USING A HIDDEN MARKOV MODEL

METHOD, A SYSTEM AND A COMPUTER-READABLE RECORDING MEDIUM FOR CORRECTING A RESULT OF OCR, PARTICULARLY USING A HIDDEN MARKOV MODEL

机译:用于校正OCR结果的方法,系统和计算机可读记录介质,尤其是使用隐藏的马尔可夫模型

摘要

PURPOSE: A method, a system and a computer-readable recording medium for correcting a result of OCR are provided to supply a character recognition result which does not requires an unnecessary line change function.;CONSTITUTION: A character recognition unit(220) performs a character recognition operation for the contents including character information by using an OCR(Optical Character Recognition) technology, and outputs a character recognition result by removing line change information for changing the rest lines except the information of the line change which indicates a line start point and the line end point. A language model(240) receives the outputted result and modifies the space for the result.;COPYRIGHT KIPO 2010
机译:目的:提供一种用于校正OCR结果的方法,系统和计算机可读记录介质,以提供不需要不必要的换行功能的字符识别结果。;组成:字符识别单元(220)执行通过使用OCR(光学字符识别)技术对包括字符信息的内容进行字符识别操作,并通过除去用于改变其余行的行改变信息(指示行起点和行的信息除外)来输出字符识别结果,该行改变信息用于更改其余行线终点。语言模型(240)接收输出的结果并修改结果的空间。; COPYRIGHT KIPO 2010

著录项

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号