Commit History

Author SHA1 Message Date
  kernel.h@qq.com 744b3f75eb 合并居中显示、想同行高的文字 1 year ago
  kernel.h@qq.com 2e772467ee 连接跨页的list 1 year ago
  xu rui 05161c6e62 feat: backup footnote_bbox_tmp 1 year ago
  xu rui 15c8830416 feat: comment parse_title 1 year ago
  xu rui 432e1ae5e3 feat: process title and footnote 1 year ago
  kernel.h@qq.com e3e125baef 跨layout的列表合并 1 year ago
  赵小蒙 2277e31ff4 ocr_demo main函数精简 1 year ago
  赵小蒙 7d010e1969 ocr_mk_mm_markdown_with_para和ocr_mk_mm_markdown_with_para_and_pagination逻辑优化 1 year ago
  赵小蒙 dbe79ba1b2 ocr_mk_mm_markdown_with_para_and_pagination逻辑更新 1 year ago
  kernel.h@qq.com f36c26565e 使用面积占比方式判断一行文本是不是在一个layoutbox里 1 year ago
  赵小蒙 a36ef4f8d5 更新pymupdf依赖版本 1 year ago
  赵小蒙 e9aa103cae ocr增加分页markdown输出格式 1 year ago
  赵小蒙 27c080a944 pipeline调整 1 year ago
  赵小蒙 b94fd7f068 Merge remote-tracking branch 'origin/master' 1 year ago
  赵小蒙 755ea5b049 更新依赖列表,增加wordninja 1 year ago
  赵小蒙 99055af331 英文文本拼接时,如果单个单词超过15个字符,则对该单词进行切分处理。行间公式/图片/表格独立占有一行 1 year ago
  icecraft 36e86dcbc5 Merge pull request #7 from myhloli/feat/add_layout 1 year ago
  许瑞 4f1f7d62d5 feat: add layout 1 year ago
  赵小蒙 1d5d778197 qa版本最终阶段保留pdf_intermediate_dict信息 1 year ago
  赵小蒙 90ea9096e5 部分layout最底部的文本圈不全,降低阈值减少底边文本被丢弃的可能性 1 year ago
  赵小蒙 0dbbf9c362 解决'[]'括起来的文本被识别成链接的问题 1 year ago
  kernel.h@qq.com 8e3beebd1a 修复index越界错误 1 year ago
  icecraft 439c18f9c4 Merge pull request #6 from myhloli/feat/add_extract_train_data 1 year ago
  许瑞 390fdb2cd5 fix: fix typo 1 year ago
  许瑞 09269c845e feat: add extract_train_data 1 year ago
  kernel.h@qq.com 056aed8677 制作OCR markdown 1 year ago
  kernel.h@qq.com ef5d9137f4 实现对论文中列表的识别 1 year ago
  赵小蒙 c5624ace1e line_to_standard_format 逻辑更新 1 year ago
  kernel.h@qq.com d062bb6ce9 merge 1 year ago
  赵小蒙 a4a9fd6934 Merge remote-tracking branch 'origin/master' 1 year ago