Extracting Numbers from JPG Files and Removing Shadings

Python
,
1

I have an example here and I’m stuck. I want to import a JPG file and extract the number from it. I want to remove the shading and only retain the contours in the middle. Is there a way to accomplish this effectively?

import cv2
import pytesseract
import numpy as np

# Path to the marked file
marking_path = "markierung_4.jpg"

# Method for preprocessing the image
def preprocess_image(image):
    # Convert the image to grayscale
    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)

    # Apply adaptive thresholding
    thresh = cv2.adaptiveThreshold(gray, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY_INV, 11, 2)

    # Use morphological operations to improve the contours
    kernel = np.ones((3, 3), np.uint8)
    eroded = cv2.erode(thresh, kernel, iterations=1)
    dilated = cv2.dilate(eroded, kernel, iterations=1)

    # Display the preprocessing steps as images
    cv2.imshow("Original Image", image)
    cv2.imshow("Grayscale", gray)
    cv2.imshow("Threshold", thresh)
    cv2.imshow("Preprocessed Image", dilated)
    cv2.waitKey(0)
    cv2.destroyAllWindows()

    return dilated

# Method for number recognition using Tesseract
def recognize_numbers(image):
    recognized_text = pytesseract.image_to_string(image, config='--psm 10 --oem 3')
    return recognized_text

# Load the marked image
marked_image = cv2.imread(marking_path)

if marked_image is not None:
    # Preprocess the image
    preprocessed_image = preprocess_image(marked_image)

    # Recognize numbers using Tesseract
    recognized_number = recognize_numbers(preprocessed_image)

    print("Recognized Number:", recognized_number)
else:
    print(f"Error loading the image {marking_path}")

Here the original Photo:
markierung_4

and the result is:
Recognized Number: 4)