首页> 外国专利> Redigitization system and service

Redigitization system and service

机译:再数字化系统和服务

摘要

A kind of system and method are disclosed for error correction existing electric document. Electronic document can be grating and turn to pixel expression electronic document (for example, raster image). The execution optical character identification (OCR) of one or more tasks can be in the electronic document of the raster image. It was found that the error mistake that can be corrected and be customized by OCR tasks corrected the electronic document of version and can be created and store. If the author of electronic document be it is known, raster image can dictionary the author associated with personalized tf*idf mistakes to determine known OCR mistakes specific to author. Raster image is also possible to dictionary the author associated with individual electronic mistake to determine known literal error specific to author.
机译:公开了一种用于纠错现有电子文档的系统和方法。电子文档可以被光栅化并转换为像素表达电子文档(例如,光栅图像)。一个或多个任务的执行光学字符识别(OCR)可以在光栅图像的电子文档中。发现可以由OCR任务纠正和定制的错误纠正了版本的电子文档并可以创建和存储。如果电子文档的作者是已知的,则光栅图像可以字典与个性化tf * idf错误相关联的作者,以确定特定于作者的已知OCR错误。光栅图像还可字典与单个电子错误相关的作者,以确定特定于作者的已知文字错误。

著录项

  • 公开/公告号US9330323B2

    专利类型

  • 公开/公告日2016-05-03

    原文格式PDF

  • 申请/专利权人 STEVEN J SIMSKE;SAMSON J. LIU;

    申请/专利号US201214364743

  • 发明设计人 STEVEN J SIMSKE;SAMSON J. LIU;

    申请日2012-04-29

  • 分类号G06K9/18;G06K9/03;G06K9/00;

  • 国家 US

  • 入库时间 2022-08-21 14:29:21

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