AI-102 Implement computer vision solutions Practice Question
A media company needs to automatically generate descriptive captions for thousands of archived photographs stored in Azure Blob Storage. The solution must be fully managed and require no model training. Which Azure AI Vision capability should they use?
⚠ Common exam trap
The trap here is assuming that any Azure AI service that processes images can generate captions, when only Azure AI Vision's image captioning feature provides that specific prebuilt capability.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Image captioning in Azure AI Vision
Image captioning in Azure AI Vision is a prebuilt feature that generates natural language descriptions for images without any training. The media company can process each stored photograph and receive a caption, directly meeting the scenario's need for automated, managed captioning. Other options either require training, target documents, or focus only on faces, so they do not provide the required broad image description.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Custom Vision classification model
Why it's wrong here
Custom Vision classification requires labeled training images and a training phase before it can classify new images. It outputs class labels, not natural language captions. Building and maintaining a custom model would add unnecessary effort and still not directly produce descriptive sentences, so it does not satisfy the no-training, caption-generation need.
- ✗
Face API person identification
Why it's wrong here
The Face API identifies or verifies individuals based on facial features. It does not describe scenes, objects, or activities in photographs. Using it on archived photos would only detect and possibly recognize faces, providing no captions about the overall image content. Thus it cannot fulfill the requirement for descriptive captions across a diverse photo archive.
- ✗
Azure AI Document Intelligence prebuilt receipt model
Why it's wrong here
Document Intelligence is designed to extract structured data from documents such as receipts, invoices, and forms. It does not analyze general photographs or generate descriptive captions. Applying it to archived photos would fail because the service expects document layouts with text, not arbitrary imagery, making it unsuitable for this media captioning scenario.
- ✓
Image captioning in Azure AI Vision
Why this is correct
Azure AI Vision's image captioning feature generates human-readable descriptions for images without any training. It is a prebuilt capability available through the Image Analysis API, ideal for captioning large archives. The media company can call this API on each blob and store the returned caption, meeting the no-training requirement.
Quick reference
Azure Blob Storage Tier Comparison
| Tier | Storage Cost | Retrieval Cost | Latency | Use Case |
|---|---|---|---|---|
| Hot | Highest | Lowest | Immediate | Active data, frequent reads |
| Cool | Lower | Higher | Immediate | Data accessed < once / month |
| Cold | Lower still | Higher | Immediate | Data accessed < once / quarter |
| Archive | Lowest | Highest + rehydration delay | Hours | Long-term compliance retention |
Go deeper
Related to this question
About these practice questions
Courseiva writes every AI-102 question from scratch — 761 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or dumps. Learn why practice questions differ from exam dumps →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official Microsoft exam blueprint
This AI-102 practice question is part of Courseiva's free Microsoft certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AI-102 exam.