pyobjc-framework-vision

import os import Vision from Foundation import NSURL, NSDictionary from Cocoa import CIImage # Often found in Quartz, but CIImage is exposed via Cocoa as well for convenience def recognize_text_in_image(image_path): if not os.path.exists(image_path): print(f"Error: Image not found at {image_path}") return # Convert Python path to NSURL input_url = NSURL.fileURLWithPath_(image_path) # Create CIImage from the URL input_image = CIImage.imageWithContentsOfURL_(input_url) if input_image is None: print(f"Error: Could not create CIImage from {image_path}") return # Create a Vision request handler vision_options = NSDictionary.dictionaryWithDictionary_({}) vision_handler = Vision.VNImageRequestHandler.alloc().initWithCIImage_options_( input_image, vision_options ) # Prepare a text recognition request results = [] def completion_handler(request, error): if error: print(f"Vision request error: {error}") else: for observation in request.results(): if isinstance(observation, Vision.VNRecognizedTextObservation): for text_candidate in observation.topCandidates_(1): results.append(text_candidate.string()) text_request = Vision.VNRecognizeTextRequest.alloc().initWithCompletionHandler_( completion_handler ) # Perform the request error_ptr = None # PyObjC expects None for output pointers that aren't being used for input success, error = vision_handler.performRequests_error_([text_request], error_ptr) if not success: print(f"Failed to perform Vision request: {error}") return results # Example usage: # Create a dummy image file for demonstration # In a real scenario, replace this with a path to an actual image file. # For a real image with text, you might create one using Pillow or similar. dummy_image_path = os.environ.get('VISION_TEST_IMAGE_PATH', 'dummy_image_with_text.png') if not os.path.exists(dummy_image_path): print(f"Please set VISION_TEST_IMAGE_PATH or create a file named '{dummy_image_path}' to run this example.") print("Example: create a simple PNG with some text using an image editor.") else: print(f"Analyzing image: {dummy_image_path}") detected_text = recognize_text_in_image(dummy_image_path) if detected_text: print("Detected text:") for text in detected_text: print(f"- {text}") else: print("No text detected or an error occurred.")