Text_recognition 1.0

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')
img = cv2.resize(img, None, fx=1.5, fy=1.5, interpolation=cv2.INTER_CUBIC)
# Convert to gray
img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

# Apply dilation and erosion to remove some noise
kernel = np.ones((1, 1), np.uint8)
img = cv2.dilate(img, kernel, iterations=1)
img = cv2.erode(img, kernel, iterations=1)

# Apply blur to smooth out the edges
#img = cv2.GaussianBlur(img, (5, 5), 0)
#img = cv2.bilateralFilter(img,9,75,75)
img = cv2.medianBlur(img, 3)

# Apply threshold to get image with only b&w (binarization)
img = cv2.threshold(img, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)[1]
cv2.threshold(img,127,255,cv2.THRESH_BINARY)
cv2.adaptiveThreshold(img, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY, 31, 2)

# selection and output of the found words on the picture
custom_config = r'-c tessedit_char_whitelist=!$&()-./0123456789@ABCDEFGHIJKLMNOPQRSTUVWXYZ\\_abcdefghijklmnopqrstuvwxyz --oem 3 --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:
        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:
        continue
# output of the result
cv2.imshow("Output", img)
cv2.waitKey(0)