[FIXED] Live Screen Monitoring With Python3 Pytesseract

Issue

I am working on a python3 project on windows 10, and I was wondering if anyone knew of anyway to pass an opencv screen grab through pytesseract? If not, is there any other OCR that you could?

Here is the code for the opencv screen grab:

import numpy as np
from PIL import ImageGrab
import cv2



while True:
    screen =  np.array(ImageGrab.grab(bbox=(0,40,800,640)))
    cv2.imshow('window', cv2.cvtColor(screen, cv2.COLOR_BGR2GRAY))
    if cv2.waitKey(25) & 0xFF == ord('q'):
        cv2.destroyAllWindows()

Solution

I know very little about pytesseract, but this might get you started:

#!/usr/bin/env python3

import numpy as np
from PIL import ImageGrab
import pytesseract
from PIL import Image, ImageEnhance, ImageFilter
from textblob import TextBlob

# Grab some screen
screen =  ImageGrab.grab(bbox=(0,0,800,640))
# Make greyscale
w = screen.convert('L')

# Save so we can see what we grabbed
w.save('grabbed.png')

text = pytesseract.image_to_string(w)
correctedText = TextBlob(text).correct()

print(correctedText)

From this grab:

I got:

@ Terminal Shell Edit View Window Help

The writing is on the wall

Answered By - Mark Setchell