I have some images, I am preprocessing them before extracting digits from them. The problem is “Tesseract” is not able to extract accurate digits from them. The images only contain digits.

Following is my code:

from PIL import Image, ImageEnhance, ImageFilter
import pytesseract


CAPTCHA_PATH = 'captcha_images/captcha8.jpeg'
RED_REMOVED_PATH = 'processed/red_removed.jpeg'
PROCESSED_IMAGE_PATH = 'processed/processed_image.png'


def change_pixels_except_black(image_path, output_path, threshold=50):
    """
    Change all pixels to white except for pixels close to black.

    :param image_path: Path to the input image.
    :param output_path: Path to save the output image.
    :param threshold: Threshold to determine if a pixel is black (default is 50).
    """
    # Open the image
    image = Image.open(image_path)
    image = image.convert("RGB")  # Ensure the image is in RGB mode

    # Load the image data
    pixels = image.load()

    # Get the dimensions of the image
    width, height = image.size

    # Iterate over each pixel
    for y in range(height):
        for x in range(width):
            # Get the current pixel's color
            r, g, b = pixels[x, y]

            # Check if the pixel is close to black
            if r < threshold and g < threshold and b < threshold:
                # Keep the pixel as is (close to black)
                continue
            else:
                # Change the pixel to white
                pixels[x, y] = (255, 255, 255)

    # Save the modified image
    image.save(output_path)


def preprocess_image(image_path, output_path):
    """
    Preprocess the image to enhance its quality for OCR.

    :param image_path: Path to the input image.
    :param output_path: Path to save the processed image.
    """
    
    # Open the image
    image = Image.open(image_path)

    # Resize the image
    new_width = image.width * 2
    new_height = image.height * 2
    image = image.resize((new_width, new_height), Image.LANCZOS)

    # Convert to grayscale
    image = image.convert('L')

    # Increase contrast
    enhancer = ImageEnhance.Contrast(image)
    image = enhancer.enhance(2)

    # Apply a filter to sharpen the image
    image = image.filter(ImageFilter.SHARPEN)

    # Save the processed image
    image.save(output_path)


def extract_text(image_path):
    """
    Extract text from an image using pytesseract.

    :param image_path: Path to the input image.
    :return: Extracted text.
    """
    text = pytesseract.image_to_string(Image.open(
        image_path), lang='eng', config='--psm 10 --oem 3 -c tessedit_char_whitelist=0123456789')

    return text


# Example usage
change_pixels_except_black(CAPTCHA_PATH, RED_REMOVED_PATH, threshold=70)
preprocess_image(RED_REMOVED_PATH, PROCESSED_IMAGE_PATH)
text = extract_text(PROCESSED_IMAGE_PATH)
print(f"Extracted Text of {CAPTCHA_PATH}:")
print(text)

These are some examples of images:

Original Image

Removed red lines

After Preprocessing

Output: 0858

Expected Output: 08588

Some other examples

Output: 95415

Expected Output: 92412

Output: 2043

Expected Output: 20413

Output: 61416

Expected Output: 61116

I have also tried different “Tesseract” configurations with no success. Please let me know if further details are required.