Azure AI Vision, image analysis, Python

--- name: azure-ai-vision-imageanalysis-py description: Azure AI Vision Image AnalysisSDK for captions, tags, objects, OCR, people detection, and smart cropping. Use for computer vision and image understanding tasks. risk: unknown source: community date_added : '2026-02-27' --- # Azure AI Vision Image AnalysisSDK for Python Client library for Azure AI Vision 4.0 image analysis, including captions, tags, objects, OCR, and more. ## Installation ``bash pip install azure-ai-vision-imageanalysis ` ## Environment Variables `bash VISION_ENDPOINT=https://<resource>.cognitiveservices.azure.com VISION_KEY=<your-api-key> # If using API key ` ## Authentication ### API Key `python import os from azure.ai.vision.imageanalysis import ImageAnalysisClient from azure.core.credentials import AzureKeyCredential endpoint = os.environ["VISION_ENDPOINT"] key = os.environ["VISION_KEY"] client = ImageAnalysisClient( endpoint=endpoint, credential=AzureKeyCredential(key) ) ` ### Entra ID (Recommended) `python from azure.ai.vision.imageanalysis import ImageAnalysisClient from azure.identity import DefaultAzureCredential client = ImageAnalysisClient( endpoint=os.environ["VISION_ENDPOINT"], credential=DefaultAzureCredential() ) ` ## Analyze Image from URL `python from azure.ai.vision.imageanalysis.models import VisualFeatures image_url = "https://example.com/image.jpg" result = client.analyze_from_url( image_url=image_url, visual_features=[ VisualFeatures.CAPTION, VisualFeatures.TAGS, VisualFeatures.OBJECTS, VisualFeatures.READ, VisualFeatures.PEOPLE, VisualFeatures.SMART_CROPS, VisualFeatures.DENSE_CAPTIONS ], gender_neutral_caption=True, language="en" ) ` ## Analyze Image from File `python with open("image.jpg", "rb") as f: image_data = f.read() result = client.analyze( image_data=image_data, visual_features=[VisualFeatures.CAPTION, VisualFeatures.TAGS] ) ` ## Image Caption `python result = client.analyze_from_url( image_url=image_url, visual_features=[VisualFeatures.CAPTION], gender_neutral_caption=True ) if result.caption: print(f"Caption: {result.caption.text}") print(f"Confidence: {result.caption.confidence:.2f}") ` ## Dense Captions (Multiple Regions) `python result = client.analyze_from_url( image_url=image_url, visual_features=[VisualFeatures.DENSE_CAPTIONS] ) if result.dense_captions: for caption in result.dense_captions.list: print(f"Caption: {caption.text}") print(f" Confidence: {caption.confidence:.2f}") print(f" Bounding box: {caption.bounding_box}") ` ## Tags `python result = client.analyze_from_url( image_url=image_url, visual_features=[VisualFeatures.TAGS] ) if result.tags: for tag in result.tags.list: print(f"Tag: {tag.name} (confidence: {tag.confidence:.2f})") ` ## Object Detection `python result = client.analyze_from_url( image_url=image_url, visual_features=[VisualFeatures.OBJECTS] ) if result.objects: for obj in result.objects.list: print(f"Object: {obj.tags[0].name}") print(f" Confidence: {obj.tags[0].confidence:.2f}") box = obj.bounding_box print(f" Bounding box: x={box.x}, y={box.y}, w={box.width}, h={box.height}") ` ## OCR (Text Extraction) `python result = client.analyze_from_url( image_url=image_url, visual_features=[VisualFeatures.READ] ) if result.read: for block in result.read.blocks: for line in block.lines: print(f"Line: {line.text}") print(f" Bounding polygon: {line.bounding_polygon}") # Word-level details for word in line.words: print(f" Word: {word.text} (confidence: {word.confidence:.2f})") ` ## People Detection ``python result = client.analyzefromurl ( imageurl =imageurl , visualfeatures = [VisualFeatures.PEOPLE] ) if result.people: for person in result.people.list: print(f"Person detected:") print(f" Confidence: {person.confidence:.2f}") box = person.boundingbox pri