MinerU处理PDF文档后导出的markdown文件中,图片是否能做到不以链接形式显示,而是直接放图片识别后结构化文本或语义描述 #3453
Unanswered
LittleCarp0314
asked this question in
Q&A
Replies: 1 comment
-
Hi @LittleCarp0314! I'm Dosu and I’m helping the MinerU team. MinerU 目前在 markdown 输出中,图片只能以链接形式引用图片文件,并不会将图片内容识别为结构化文本或语义描述直接嵌入 markdown 文件。MinerU 不会对 PDF 图片区域做 OCR 或图像内容分析,只是裁剪图片区域输出为图片。如需图片内的文字或语义描述,需要借助外部 OCR 或图像描述工具,先识别图片内容,再手动插入 markdown 文件。目前 MinerU 没有相关配置项或插件支持自动实现这一需求,也没有官方 roadmap 计划支持该功能[参考1][参考2]。 To reply, just mention @dosu. How did I do? Good | Irrelevant | Incorrect | Verbose | Hallucination | Report 🐛 | Other |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
MinerU目前在markdown输出中处理图片的方式是以链接形式引用图片文件,在markdown文件中显示图片部分,是否可以不以链接形式显示,而是直接放图片识别后结构化文本或语义描述?
Beta Was this translation helpful? Give feedback.
All reactions