Azure AI Vision Imageanalysis Py

Azure AI Vision Image Analysis SDK for Python

Client library for Azure AI Vision 4.0 image analysis including captions, tags, objects, OCR, and more.

Installation

pip install azure-ai-vision-imageanalysis

Environment Variables

VISION_ENDPOINT=https://<resource>.cognitiveservices.azure.com  # Required for all auth methods
VISION_KEY=<your-api-key>  # Only required for AzureKeyCredential auth
AZURE_TOKEN_CREDENTIALS=prod # Required only if DefaultAzureCredential is used in production

Authentication

API Key

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)

import os
from azure.ai.vision.imageanalysis import ImageAnalysisClient
from azure.identity import DefaultAzureCredential, ManagedIdentityCredential

# Local dev: DefaultAzureCredential. Production: set AZURE_TOKEN_CREDENTIALS=prod or AZURE_TOKEN_CREDENTIALS=<specific_credential>
credential = DefaultAzureCredential(require_envvar=True)
# Or use a specific credential directly in production:
# See https://learn.microsoft.com/python/api/overview/azure/identity-readme?view=azure-python#credential-classes
# credential = ManagedIdentityCredential()

client = ImageAnalysisClient(
    endpoint=os.environ["VISION_ENDPOINT"],
    credential=credential
)

Analyze Image from URL

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

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

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)

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

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

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)

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

result = client.analyze_from_url(
    image_url=image_url,
    visual_features=[VisualFeatures.PEOPLE]
)

if result.people:
    for person in result.people.list:
        print(f"Person detected:")
        print(f"  Confidence: {person.confidence:.2f}")
        box = person.bounding_box
        print(f"  Bounding box: x={box.x}, y={box.y}, w={box.width}, h={box.height}")

Smart Cropping

result = client.analyze_from_url(
    image_url=image_url,
    visual_features=[VisualFeatures.SMART_CROPS],
    smart_crops_aspect_ratios=[0.9, 1.33, 1.78]  # Portrait, 4:3, 16:9
)

if result.smart_crops:
    for crop in result.smart_crops.list:
        print(f"Aspect ratio: {crop.aspect_ratio}")
        box = crop.bounding_box
        print(f"  Crop region: x={box.x}, y={box.y}, w={box.width}, h={box.height}")

Async Client

from azure.ai.vision.imageanalysis.aio import ImageAnalysisClient
from azure.identity.aio import DefaultAzureCredential

async def analyze_image():
    async with ImageAnalysisClient(
        endpoint=endpoint,
        credential=DefaultAzureCredential()
    ) as client:
        result = await client.analyze_from_url(
            image_url=image_url,
            visual_features=[VisualFeatures.CAPTION]
        )
        print(result.caption.text)

Visual Features

Error Handling

from azure.core.exceptions import HttpResponseError

try:
    result = client.analyze_from_url(
        image_url=image_url,
        visual_features=[VisualFeatures.CAPTION]
    )
except HttpResponseError as e:
    print(f"Status code: {e.status_code}")
    print(f"Reason: {e.reason}")
    print(f"Message: {e.error.message}")

Image Requirements

• Formats: JPEG, PNG, GIF, BMP, WEBP, ICO, TIFF, MPO
• Max size: 20 MB
• Dimensions: 50x50 to 16000x16000 pixels

Best Practices

1. Select only needed features to optimize latency and cost
2. Use async client for high-throughput scenarios
3. Handle HttpResponseError for invalid images or auth issues
4. Enable gender_neutral_caption for inclusive descriptions
5. Specify language for localized captions
6. Use smart_crops_aspect_ratios matching your thumbnail requirements
7. Cache results when analyzing the same image multiple times