[TODO] `create_features` does not detect rotated images leading to no extractions

[shabie]

TODO

I specially like this answer with tesserocr (faster than pytesseract): https://stackoverflow.com/a/69131832/7996306

[uakarsh]

Okay, I would try to include that, instead of pytesseract. Just a side note, did you add the DocFormer implementation, in the paperswithcode.com :)

[uakarsh]

I am trying it, however I face this error https://githubmemory.com/repo/madmaze/pytesseract/issues/368, and I am unable to fix it right now.

[uakarsh]

I am trying it, however, I face this error https://githubmemory.com/repo/madmaze/pytesseract/issues/368, and I am unable to fix it right now.

I would try to fix it in coming days

[shabie]

I'll try to get on it in the next days.

On Fri, Nov 19, 2021, 10:26 uakarsh @.***> wrote:

I am trying it, however, I face this error https://githubmemory.com/repo/madmaze/pytesseract/issues/368, and I am unable to fix it right now.

I would try to fix it in coming days

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/shabie/docformer/issues/15#issuecomment-973900960, or unsubscribe https://github.com/notifications/unsubscribe-auth/AHI632WG2BW3J4LM4EWZDLLUMYJ5DANCNFSM5HYBDUVQ .

[shabie]

So as an update, despite my best attempts I haven't manage to get the OCR any bit faster...

[uakarsh]

So, uptil then, let us try to work with our old conventional method