PaddleOCR icon indicating copy to clipboard operation
PaddleOCR copied to clipboard

增值税发票结构化识别

Open ZTurboX opened this issue 2 years ago • 2 comments

增值税发票结构化识别是什么思路呢?

ZTurboX avatar Jul 30 '22 05:07 ZTurboX

  1. 传统思路:可以直接用ocr检测识别+模板匹配
  2. 可以使用关键信息抽取的方法,去做文档vqa任务

场景非常固定的话,建议第一种,成本会低一些,如果考虑扩展性,可以用第二种

littletomatodonkey avatar Aug 08 '22 15:08 littletomatodonkey

用第一种方法,ocr检测结果会把单元格内的多行文本分开

ZTurboX avatar Aug 09 '22 00:08 ZTurboX

This issue has been automatically marked as stale because it has not had recent activity. It will be closed in 7 days if no further activity occurs. Thank you for your contributions.

github-actions[bot] avatar Jul 07 '23 08:07 github-actions[bot]