Check the API:
https://pypi.org/project/pytesseract/
There is an example under: Support for OpenCV image/NumPy array objects
You may also try different languages (I had different results just on
numbers).
Il giorno gio 31 gen 2019 alle ore 15:18 Aaron Spell <8383...@gmail.com> ha
scritto:
>
Lorenzo Blz, thanks for your reply
PSM 13 results are better than PSM 6
crop white border not give some results
will try to train tesseract.
*How can I send byte array to Tesseract from avoid saving and open picture
to the hard disk?*
среда, 30 января 2019 г., 17:25:26 UTC+3 пользователь
Try psm 6
Try a few small upscales so that the text is between 30-40 px and see if it
helps, like 31, 33, 35, 37, 39 (on a large test set).
Try to crop all the white border (imagemagick, gimp) and see if it helps.
Otherwise you need to fine tune the model:
https://github.com/tesseract-ocr/tesse
*Hi! I'm started using to tesseract with python and have some questions*
*This example how i trying get recognized image:*
import pytesseract
from PIL import Image
pytesseract.pytesseract.tesseract_cmd = r'c:\Program Files
(x86)\Tesseract-OCR\tesseract.exe'
x = Image.open("err1.png")
text =
4 matches
Mail list logo
