小型规则图片会被识别为字符并且因为无法识别而用“乐”占位,而不会直接保存为图片 #4625
Unanswered
oybeestert-engsher
asked this question in
Q&A
Replies: 1 comment
-
|
Hi @oybeestert-engsher! I'm Dosu and I’m helping the MinerU team. 这个问题在 MinerU 中确实存在,主要发生在使用 VLM 后端时,模型可能会将小图片误识别为字符。 建议的解决方案:
当前限制:MinerU 目前没有可配置的图片大小阈值参数,区域类型识别依赖深度学习模型的分类结果。VLM 后端的图片拆分问题计划在未来版本修复。 如果可以分享具体的 PDF 文件或更多细节,可能有助于开发者进一步排查问题。 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.
-
Beta Was this translation helpful? Give feedback.
All reactions