tesserocr

import tesserocr from PIL import Image from io import BytesIO import base64 # A simple base64 encoded image containing "Hello World" for a runnable example # In a real scenario, you'd load an image from file: Image.open("path/to/image.png") img_data = "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" image_bytes = base64.b64decode(img_data) image = Image.open(BytesIO(image_bytes)) # Initialize Tesseract API # You might need to specify lang='eng' or tessdata_dir='path/to/tessdata' # if Tesseract is not configured globally or language files are not found. api = tesserocr.PyTessBaseAPI(lang='eng') api.SetImage(image) text = api.GetUTF8Text() confidence = api.MeanTextConf() api.End() print(f"Detected Text: {text.strip()}") print(f"Confidence: {confidence}") # Shorter convenience function for quick OCR text_short = tesserocr.image_to_text(image, lang='eng') print(f"Detected Text (short function): {text_short.strip()}") # Example of getting Tesseract version print(f"Tesseract Version: {tesserocr.get_tesseract_version()}")