Python Image to Text

main.py

# Dependencies: pip install opencv-python-headless pytesseract numpy

import cv2
import pytesseract
import matplotlib.pyplot as plt

# Path to Tesseract executable (change this according to your installation)
pytesseract.pytesseract.tesseract_cmd = r'C:\Program Files (x86)\Tesseract-OCR\tesseract.exe'

def capture_and_parse_text():
    while True:
        # Activate camera
        cap = cv2.VideoCapture(0)

        if not cap.isOpened():
            print("Error: Could not open camera.")
            return

        # Capture a frame
        ret, frame = cap.read()

        if not ret:
            print("Error: Failed to capture image.")
            cap.release()
            return

        # Show preview of the captured image using matplotlib
        plt.imshow(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB))
        plt.axis('off')
        plt.title('Captured Image')
        plt.show()

        # Save the captured image
        image_path = "captured_image.jpg"
        cv2.imwrite(image_path, frame)
        print("Image captured successfully.")

        # Release the camera
        cap.release()

        # Parse text from the captured image
        parsed_text = parse_text_from_image(image_path)
        print("Parsed text from image:")
        print(parsed_text)

        # Ask user if they want to retry parsing
        retry = input("Do you want to retry parsing the image? (y/n): ")
        if retry.lower() != 'y':
            break

def parse_text_from_image(image_path):
    # Read the image using OpenCV
    img = cv2.imread(image_path)

    # Convert image to grayscale
    # gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

    # Use pytesseract to perform OCR
    parsed_text = pytesseract.image_to_string(img, lang="deu")

    return parsed_text.replace("\n\n", "").replace("\n", " ")

if __name__ == "__main__":
    capture_and_parse_text()