Study guide

3.1 Azure AI Vision — Image Analysis 4.0

Azure AI Engineer Associate AI-102

Track your progress as you read

Finished sections get a check mark.

1 Introduction

About the Azure AI Engineer Associate (AI-102) Exam Study Strategies and Exam Tips for the AI-102

2 Domain 1: Plan and Manage an Azure AI Solution (20-25%)

1.1 Azure AI Services Overview and Selection 1.2 Resource Provisioning and Configuration 1.3 Security and Access Management 1.4 Responsible AI Principles and Implementation 1.5 Azure AI Solution Architecture Patterns

3 Content Safety and Moderation (within Plan and Manage, Domain 1)

2.1 Azure AI Content Safety Overview 2.2 Prompt Shields and Adversarial Attack Detection 2.3 Text and Image Moderation Implementation 2.4 Content Filtering in Azure OpenAI Service

4 Domain 4: Implement Computer Vision Solutions (10-15%)

3.1 Azure AI Vision — Image Analysis 4.0 3.2 Azure AI Face Service 3.3 Azure AI Custom Vision 3.4 Optical Character Recognition (OCR) 3.5 Video Analysis and the Retired Spatial Analysis

5 Domain 5: Implement Natural Language Processing Solutions (15-20%)

4.1 Azure AI Language — Text Analytics Features 4.2 Conversational Language Understanding (CLU) 4.3 Custom Text Classification and Custom NER 4.4 Azure AI Speech Services 4.5 Azure AI Translator Service 4.6 Question Answering and Conversational AI

6 Domain 6: Implement Knowledge Mining and Information Extraction Solutions (15-20%)

5.1 Azure AI Search — Fundamentals and Architecture 5.2 AI Enrichment with Skillsets 5.3 Azure AI Document Intelligence

7 Domain 2: Implement Generative AI Solutions (15-20%)

6.1 Azure OpenAI Service — Models and Deployment 6.2 Chat Completions API and Prompt Engineering 6.3 Embeddings and Vector Search for RAG 6.4 Fine-Tuning and Model Customization 6.5 Image Generation (gpt-image; DALL-E 3 Retired) 6.6 RAG After On Your Data, and AI Agents

8 Domain 3: Implement an Agentic Solution (5-10%)

3.1 Agentic Solutions: Foundry Agent Service and the Microsoft Agent Framework

9 Exam Review: Cross-Domain Topics and Advanced Practice

7.1 Service Comparison and Selection Guide 7.2 SDK and REST API Patterns 7.3 Responsible AI Across All Domains 7.4 End-to-End Solution Architectures 7.5 Exam Day Quick Reference

3.1 Azure AI Vision — Image Analysis 4.0

Key Takeaways Explain This Topic AI

Image Analysis 4.0 delivers captioning, dense captions, tagging, object detection, people detection, smart crops, and OCR in a single Analyze call powered by the Florence foundation model.

Visual features are passed as a list (Caption, DenseCaptions, Tags, Objects, People, SmartCrops, Read); only requested features are billed and returned.

Caption and DenseCaptions are GA only in a limited set of Azure regions; requesting Caption from an unsupported region returns an error, a frequent exam scenario.

Input accepts a public URL or binary bytes up to 20 MB, between 50x50 and 16000x16000 pixels, in JPEG, PNG, GIF, BMP, WEBP, ICO, TIFF, or MPO.

Image Analysis 4.0 custom classification and object detection models were retired on March 31, 2025; Microsoft points users who need a trained image model to Azure AI Custom Vision.

Last updated: October 2026

Quick Answer: Image Analysis 4.0 uses the Florence foundation model to return captioning, dense captions, tags, objects, people, smart crops, and OCR from a single analyze call. You request features with the features (REST) or visual_features (SDK) parameter and read each one from its own result object. Caption and DenseCaptions are limited to specific regions.

What the Analyze API Returns

Image Analysis 4.0 is exposed at the imageanalysis:analyze endpoint and replaces the legacy Computer Vision 3.x analyze and describe operations. A single round trip can return up to seven analyses, each charged as a separate transaction.

  • Visual feature What it produces Result property
  • Caption One human-readable sentence for the whole image caption.text , caption.confidence
  • DenseCaptions Up to 10 region captions, each with a bounding box dense_captions.list[]
  • Tags Content tags with confidence (no boxes) tags.list[]
  • Objects Object class + bounding box objects.list[].tags , .bounding_box
  • People People bounding boxes + confidence people.list[]
  • SmartCrops Crop coordinates per requested aspect ratio smart_crops.list[]
  • Read Printed/handwritten text (OCR) read.blocks[].lines[].words
  • Region and Input Limits (high-value trap)

Caption and DenseCaptions are GA only in a subset of regions (East US, West US, West Europe, France Central, Korea Central, North Europe, Southeast Asia, West US 2, East Asia, Switzerland North, Sweden Central, and a few more). Tags, Objects, People, SmartCrops, and Read run in all Vision regions. If a question shows a 400/feature-unsupported error after adding Caption, the fix is to deploy the resource in a supported region — not to change the SDK.

Image bytes must be 50x50 to 16000x16000 pixels and at most 20 MB .

Set gender_neutral_caption=True to replace gendered nouns ("man", "woman") with "person" — a Responsible AI default many teams require.

smart_crops_aspect_ratios accepts values from 0.75 to 1.8 (e.g., 0.9 for portrait thumbnails, 1.33 for 4:3). Omit it and the service picks the best single crop.

Calling the API

REST — features are a comma-separated query string and the body carries the image: POST {endpoint}/computervision/imageanalysis:analyze?api-version=2024-02-01&features=caption,read,tags&gender-neutral-caption=true&language=en

  • Ocp-Apim-Subscription-Key: <key>
  • Content-Type: application/json

{ "url": "https://example.com/photo.jpg" }

Python SDK — analyze_from_url (or analyze for bytes) takes a VisualFeatures list: from azure.ai.vision.imageanalysis import ImageAnalysisClient

  • from azure.ai.vision.imageanalysis.models import VisualFeatures
  • from azure.core.credentials import AzureKeyCredential
  • client = ImageAnalysisClient(endpoint, AzureKeyCredential(key))
  • result = client.analyze_from_url(
  • image_url="https://example.com/photo.jpg",
  • visual_features=[VisualFeatures.CAPTION, VisualFeatures.TAGS,
  • VisualFeatures.OBJECTS, VisualFeatures.READ],
  • gender_neutral_caption=True,
  • language="en")
  • print(result.caption.text, result.caption.confidence)

for t in result.tags.list:

  • print(t.name, t.confidence)
  • Reading the JSON Response

Each feature lands in its own object; missing features are simply absent. Watch the property names — the exam routinely shows JSON and asks for the line that extracts a value. {

  • "captionResult": { "text": "a person walking a dog in a park", "confidence": 0.8745 },
  • "tagsResult": { "values": [ {"name":"outdoor","confidence":0.99} ] },
  • "objectsResult": { "values": [ {"tags":[{"name":"dog","confidence":0.92}],
  • "boundingBox":{"x":250,"y":300,"w":150,"h":120}} ] }
  • }
  • Worked Example

A news site needs alt text plus 16:9 and 1:1 social thumbnails from one upload. Request features=caption,smartCrops , set smart_crops_aspect_ratios=[1.78, 1.0] , set gender_neutral_caption=True , and store caption.text as alt text and each smart_crops.list[].bounding_box as a crop rectangle — one call, no separate cropping service.

Tags, Objects, and People: Subtle Distinctions

Candidates lose points by conflating the three detection features, because their outputs overlap in everyday language but differ sharply in the response. Tags are image-level keywords with confidence and no spatial location — the model may tag an image "dog" even when the dog is tiny in a corner. Objects return the same class names but each comes with a bounding_box , so you know where the dog is. People is a specialized detector that returns only person bounding boxes with confidence and is the correct choice when you must count or locate humans specifically rather than enumerate every object class.

A common scenario asks how to count shoppers in a frame for analytics: the right feature is People , not Objects filtered to "person," because People is tuned for crowded scenes and partial occlusion.

Choosing Image Analysis vs. Other Vision Services

Image Analysis 4.0 is the prebuilt, no-training option. Reach for Custom Vision (Image Analysis 4.0 custom models were retired on March 31, 2025) only when the standard tag and object taxonomy cannot name your domain concepts (for example, "cracked weld" or a specific SKU). Reach for Document Intelligence when the picture is really a document and you need fields rather than tags. The exam frequently frames this as a single-best-answer choice: if the requirement is "describe arbitrary photos and pull any visible text with zero training," the answer is Image Analysis 4.0 with Caption + Read , not a trained model.

Retired: Custom Image Analysis Models

Image Analysis 4.0 once trained custom classifiers and detectors with Florence transfer learning and called them through model_name . Microsoft retired the Image Analysis 4.0 Custom Image Classification, Custom Object Detection, and Product Recognition preview APIs on March 31, 2025 , and calls to them now fail. For a model trained on your own labeled images, Microsoft points to Azure AI Custom Vision (supported until September 25, 2028), which needs at least 5 labeled images per tag for classification and recommends 50 or more.

On the Exam: Memorize which features are region-limited (Caption, DenseCaptions), the 20 MB / 16000px input ceiling, and that gender_neutral_caption is the Responsible AI knob. For a model trained on your own labeled images, pick Custom Vision , not the retired Image Analysis custom models.