My question related to the image part not making training from text
The overall training process is similar to training 3.04 Conceptually the same:
Prepare training text.
Render text to image + box file. (Or create hand-made box files for existing image data.)
Make unicharset file.
Optionally make dictionary data.
Run tesseract to process image + box file to make training data set.
Run training on training data set.
Combine data files.
hello All,
I want to ask about this version if it supports Training of the new version of tesseract 4.0 LSTM.
And if not can anyone help in:
this is the part from https://github.com/tesseract-ocr/tesseract/wiki/TrainingTesseract-4.00
My question related to the image part not making training from text
The overall training process is similar to training 3.04 Conceptually the same:
Prepare training text.
Render text to image + box file. (Or create hand-made box files for existing image data.)
Make unicharset file.
Optionally make dictionary data.
Run tesseract to process image + box file to make training data set.
Run training on training data set.
Combine data files.
Are the above steps similar to:
Should I use these steps or not.
Thanks!!
Last edit: Ahmad Moawad 2017-04-12
Have a look at these official steps, they were made by one of the developers of tesseract, a step-by-step guide for training the Arabic language in Tesseract 4.x
https://github.com/tesseract-ocr/tesseract/wiki/TrainingTesseract-4.00---Finetune