That is perfect. I also see that you are taking advantage of OCR-D. I
firmly believe that true intelligence is revealed in the formation of the
right question more than in the one who reserves the answer.
Thank you for sharing. You have made my life much easier by suffering the
pain for yoursel
Keith,
Thank you so much for this. You are not alone. You have just clued me in.
I am about ready to start my first training run. Then I saw this in my
email box.
You may be a life saver for doing this. How are we supposed to know these
things if the docs are not updated. After looking inside
The original training scripts in tesseract repo is `tesstrain.sh` and all
training tutorials refer to that.
Make based `tesstrain` repo is a later addition and tesseract documentation
has not been updated for it.
You can contribute by creating a PR to add missing info regarding training
for the `
Shree,
Thank you for your reply. I should have gone to bed (it was like 2 AM my
time on a work night) instead of continuing to bang my head.
When I saw your message this morning, I was thinking, "What tesstrain
folder? There's no tesstrain folder in the repo." Which was exactly when it
occurred t
are there any equivalent function in OpenCV which can do similar executions
like what you did with leptonica?
On Friday, January 8, 2021 at 12:20:29 AM UTC+5:30 zdenop wrote:
> Unfortunately I am not aware of (maintained) python leptonica support (any
> volunteers?), but you can directly use le
See https://groups.google.com/g/tesseract-ocr/c/GFHIZ8hO3c4/m/ieYUckMvBgAJ
On Friday, August 7, 2020 at 10:21:11 AM UTC+5:30 ultra wrote:
> Hello zodiac,
>
> I'm trying to train vertical Japanese, but the documentation is not great
> for vertical language.
> Could you briefly describe the steps
I also want to know that how we can train on real images which are not
single lines?
On Thursday, October 8, 2020 at 1:37:02 PM UTC+5:30 smn...@gmail.com wrote:
> Hello,
>
> I would like to train *Tesseract 4* to recognize certain
> scripts/languages based on real images rather than synthetic o
It is now 2 years since this answer was posted. Is it possible to train
tesseract 4 on real images now?
On Thursday, January 11, 2018 at 2:27:43 PM UTC+5:30 shree wrote:
> Currently, Ray/Google has NOT released info on how to train Tesseract 4
> (LSTM) with real life images. The only supported
>After placing the groundtruth files in a folder called
*data/foo-ground-truth* inside the main *tesseract *repo folder,
data/foo-ground-truth needs to be under the tesstrain folder not
tesseract folder.
You can use ground-truth in a different location, in that case you have to
refer to it whi
9 matches
Mail list logo
