Questions tagged [tesstrain]
6 questions
2
votes
1 answer
Tesseract tesstrain.sh can not find the font
I am trying to train tesseract with the guide of:
https://tesseract-ocr.github.io/tessdoc/TrainingTesseract-4.00.html
But even though i did not put a font argument in my command line i get this error:
Could not find font named 'Arial Bold'.
Pango…
nour
- 398
- 3
- 7
2
votes
0 answers
Tesseract - Training vertical languages
I can't find any documentation on vert traineddata files. What do they contain? Are they the same language model only with different configuration? Should I just be training the basic model with vertical loaded as sublanguage and that would train…
L14n
- 51
- 3
2
votes
0 answers
Tesseract tesstrain.sh - Error: jpn_vert is not a valid language code
Trying to run tesstrain.sh for jpn_vert
tesstrain.sh --fonts_dir ./tesstutorial --lang jpn_vert --linedata_only --save_box_tiff --langdata_dir ./tesstutorial --fontlist 'Font' --tessdata_dir ./tesstutorial --output_dir ./result
and I'm getting…
L14n
- 51
- 3
2
votes
0 answers
Tesseract train specific characters
Is it possible to increase the accuracy of specific characters in an existing traineddata model?
For example:
The number 3 will often be detected as 5.
The number 5 will often be detected as 8.
The W will often be detected as V.
Makes it sense to…
Sean Stayns
- 4,082
- 5
- 25
- 35
0
votes
1 answer
tesseract 4 Why isn't my training data compiling
I am trying to train Tesseract 4 to recognise some electronic circuit diagram symbols such as a resistor, capacitor etc from images but there seems to be no straight forward guide into training tesseract and the official documentation seems to focus…
Charles Kelly
- 17
- 4
-1
votes
1 answer
Evaluation of a trained-on-generated images Tesseract 4 LSTM model against real images
I have trained a Tesseract 4 LSTM model against a set of ~30,000 ground truth images that I generated (as opposed to using "real" images from scanned works, of which I do not have enough to reliably train a model).
The model works well (or at least…
Inductiveload
- 6,094
- 4
- 29
- 55