openCV.py

import cv2
import numpy as np
import pytesseract
from PIL import Image

# Path of working folder on Disk
def get_string():
    # Read image with opencv
    img = cv2.imread("CVtest.png")

    # 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)

    # Write image after removed noise
    cv2.imwrite("removed_noise.png", img)

    #  Apply threshold to get image with only black and white
    #img = cv2.adaptiveThreshold(img, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY, 31, 2)

    # Recognize text with tesseract for python
    tessdata_dir_config = r'--tessdata-dir "C:\Users\Hong\AppData\Local\Tesseract-OCR"'
    result = pytesseract.image_to_string(Image.open("removed_noise.png"),config=tessdata_dir_config)

    # Remove template file
    #os.remove(temp)

    return result


print ('--- Start recognize text from image ---')
print (get_string())

print ("------ Done -------")