How do I train tesseract 4 with image data instead of a font file?

I am trying to train Tesseract 4 with images instead of fonts. In docs, they only explain the approach in fonts, not images. I know how this works when I use the previous version of Tesseract, but I did not get how to use box / tiff files for training using LSTM in Tesseract 4. I looked at tesstrain.sh , which is used to generate LSTM , but did not find anything useful. Any ideas?

+7
ocr tesseract training-data lstm
source share

No one has answered this question yet.

See similar questions:

0
Tesseract can't read math expression

or similar:

eleven
Tesseract Training for the New Font
6
Tesseract train for one specific font
6
Create a tutorial image for Tesseract OCR
5
How to create a tiff / box file from an image for training Tesseract on Windows
4
Tesseract Training - a new font with only numbers
3
Adding Blackletter Font Support to the Tesseract OCR Engine
3
Can you train tesseract with images instead of text and font?
2
Tesseract Training Data
0
Where in Windows the .tr tesseract training file is saved
0
Training tesseract 4 with images instead of font

All Articles