【24h】

Identification of Font Styles and Typefaces in Printed Korean Documents

机译:韩国印刷文件中字体样式和字体的识别

获取原文
获取原文并翻译 | 示例

摘要

This paper proposes a system for the extraction of typographical attributes, such as font style and typeface, that can be used to improve the performance of OCR and keyword spotting technologies on printed Korean document images. Three typographical features have been devised and experimented with 7,200 Korean word images. The individual accuracies for font style identification and typeface identification are 97.2% and 99.1%, respectively.
机译:本文提出了一种用于提取印刷属性(如字体样式和字样)的系统,该系统可用于提高在印刷的韩国文档图像上的OCR和关键字点技术的性能。已设计出三种印刷功能,并尝试了7,200个韩语文字图像。字体样式识别和字体识别的准确性分别为97.2%和99.1%。

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