search

openpaperwork / pyocr

A Python wrapper for Tesseract and Cuneiform -- Moved to Gnome's Gitlab
https://gitlab.gnome.org/World/OpenPaperwork/pyocr
931 stars 152 forks source link

1 recognize 3 issue #91

Closed xinyanliang closed 6 years ago

xinyanliang commented 6 years ago

digits = tool.image_to_string( im1, lang='osd', builder=DigitBuilder(), )

Will use tool 'Tesseract (sh)'

This code always recognize 1 to 3, how to fix it ?

jflesch commented 6 years ago

PyOCR is just a wrapper for Tesseract (and Cuneiform). Results depend entirely on them and their training data. --> https://github.com/tesseract-ocr/tesseract/wiki/TrainingTesseract