• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International conference on communications and cyber physical engineering >Performance Analysis of Deskewing Techniques for Offline OCR
【24h】

Performance Analysis of Deskewing Techniques for Offline OCR

机译：离线OCR的去歪斜技术性能分析

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Optical Character Recognition (OCR) is a significantly important research domain of pattern recognition. Achieving a better accuracy of recognition along with acceptable execution efficiency is a key challenge in performing the recognition task. The stage of preprocessing which assist the step of feature extraction is responsible for performing a series of operation including Deskewing to retain and maintain only that part of the information which is essential for the operation of recognition. The paper presents detailed performance analysis different skew detection methods. The analysis presented in this paper will help in deciding which method performs well for any particular script. The analysis is helpful in deciding deskewing technique for handwritten & printed script.
机译：光学字符识别（OCR）是模式识别的重要研究领域。实现更好的识别精度以及可接受的执行效率是执行识别任务的关键挑战。协助特征提取步骤的预处理阶段负责执行一系列操作，其中包括“去偏斜”，以仅保留和维护识别操作必不可少的那部分信息。本文介绍了不同的偏斜检测方法的详细性能分析。本文中提出的分析将有助于确定哪种方法对任何特定脚本的效果都很好。该分析有助于确定手写和打印脚本的去歪斜技术。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

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