OCR 1.1

import pytesseract
import cv2

pytesseract.pytesseract.tesseract_cmd = r"C:\\Program Files\\Tesseract-OCR\\tesseract.exe"

import numpy as np

img = cv2.imread('test.png')

# get grayscale image
def get_grayscale(image):
    return cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)

# noise removal
def remove_noise(image):
    return cv2.medianBlur(image, 5)

# thresholding
def thresholding(image):
    return cv2.threshold(image, 0, 255, cv2.THRESH_BINARY)[1]

# dilation
def dilate(image):
    kernel = np.ones((5, 5), np.uint8)
    return cv2.dilate(image, kernel, iterations=1)

# erosion
def erode(image):
    kernel = np.ones((5, 5), np.uint8)
    return cv2.erode(image, kernel, iterations=1)

# opening - erosion followed by dilation
def opening(image):
    kernel = np.ones((5, 5), np.uint8)
    return cv2.morphologyEx(image, cv2.MORPH_OPEN, kernel)

# canny edge detection
def canny(image):
    return cv2.Canny(image, 100, 200)

img = get_grayscale(img)
#img = remove_noise(img)
#img = thresholding(img)
#img = dilate(img)
#img = erode(img)
#img = opening(img)
#img = canny(img)

# selection and output of the found words on the picture
custom_config = r'-c tessedit_char_whitelist=abcdefghijklmnopqrstuvwxyz-\ QWERTYUIOPASDFGHJKLZXCVBNM --psm 12'
text = pytesseract.image_to_string(img, config=custom_config)
words = text.split()

with open('WordsFromWindowsScreen.txt', 'w') as f:
    for word in words:
        if (len(word) > 2): f.write(word + " ")
data = pytesseract.image_to_data(img, config=custom_config)
for i, item in enumerate(data.splitlines()):
    if i == 0:
        continue
    item = item.split()
    try:
        x, y, w, h = int(item[6]), int(item[7]), int(item[8]), int(item[9])
        cv2.rectangle(img, (x, y), (x + w, y + h), (255, 0, 0), 1)
        cv2.putText(img, item[11], (x, y), cv2.FONT_HERSHEY_COMPLEX, 1, (255, 255, 0), 1)
    except IndexError:
        print("missed")

# output of the result
cv2.imshow("Output", img)
cv2.waitKey(0)