On Wednesday, December 16, 2015 at 6:18:00 PM UTC+4, Denis McMahon wrote: > On Wed, 16 Dec 2015 06:04:37 -0800, fsn761304 wrote: > > > I'm trying to make OCR-recognition on a screenshot, after screenshot > > taken it goes to pibxbuffer, which content goes to pytesseract. > > But after using pixbuffer image quality is bad > > > image = image.resize((width*20,height*20), Image.ANTIALIAS) > > This appears to attempt to extrapolate 400 pixels from each pixel in the > original image. > > That only works on TV crime dramas, you can't do it in real life. > > -- > Denis McMahon, denismfmcma...@gmail.com
I tried also another code (see below) and without scaling by 20 quality of recognition was very bad. from pytesseract import image_to_string from PIL import Image im = Image.open("screen.png") print(im) im = im.resize((214*20,26*20), Image.ANTIALIAS) print(image_to_string(im)) -- https://mail.python.org/mailman/listinfo/python-list