This script allows you to extract English text from images using Python.

README.md

1. Install the required packages by running pip install -r requirements.txt in your terminal.
2. Run the command export TESSDATA_PREFIX=/usr/local/tessdata in your terminal to set the Tesseract data path.
3. Download the English language data from here and place it to the tessdata folder above.
4. Run main.py

main.py

import base64
import cv2
import numpy as np
import pytesseract
import requests

def download_image_from_url(url):
    response = requests.get(url)
    img_data = response.content
    return img_data

def extract_en_text(img_data):
    # Convert the image data to an OpenCV image
    np_arr = np.frombuffer(img_data, np.uint8)
    img = cv2.imdecode(np_arr, cv2.IMREAD_COLOR)

    # Increase the accuracy of text extraction using pytesseract
    custom_config = r'--oem 3'
    extracted_text = pytesseract.image_to_string(img, lang='eng', config=custom_config)
    return extracted_text

url = input("Enter the image URL: ") # demo: https://cdn.memes.com/up/2987451663882327/i/1663981590975.jpg
img_data = download_image_from_url(url)
text = extract_en_text(img_data)
print(f"Output:\n{text}")