AI-102 Implement computer vision solutions Practice Question
A media company wants to automatically generate alt text for images on its news site using Azure AI Vision. The images are stored in Azure Blob Storage, and the solution must run serverless and respond within seconds. Which approach should you use?
⚠ Common exam trap
Test-takers frequently confuse image classification or face analysis with captioning, which is the only Azure AI Vision feature that produces descriptive natural-language text.
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
✓
Deploy an Azure Function that calls the Image Analysis caption feature with the image URL and returns the generated text.
Image Analysis captioning produces a one-sentence description suitable for alt text, and it accepts either image bytes or a URL. Hosting the call in an Azure Function keeps the solution serverless and event-driven, so responses come back in seconds. Custom Vision, Face, and speech batch transcription do not generate general-purpose image descriptions and therefore cannot meet the requirement.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Deploy an Azure Function that calls the Image Analysis caption feature with the image URL and returns the generated text.
Why this is correct
Azure Functions provides a serverless compute model, and Image Analysis 4.0 can accept a publicly reachable image URL, so the function can request the caption feature and return alt text quickly. This combination meets the serverless and low-latency requirements without managing infrastructure or moving image bytes unnecessarily.
- ✗
Use the Face API to describe each image based on detected people.
Why it's wrong here
The Face API detects and analyzes faces, returning attributes like position and landmarks, not general image descriptions. It cannot describe objects, scenes, or actions in the photos, so it would produce irrelevant or empty output for most news images. This is the wrong service for generating alt text.
- ✗
Run a batch transcription job over the image files to extract descriptive text.
Why it's wrong here
Batch transcription is a speech-to-text capability that processes audio, not images. Pointing it at image blobs would fail entirely because the input format is unsupported. This option confuses speech services with vision services and cannot generate alt text from photographs.
- ✗
Create a Custom Vision classification project and train it on the site's images to produce captions.
Why it's wrong here
Custom Vision classification assigns predefined labels; it does not generate natural-language descriptions. Training would require labeled categories and would only output class names, not alt text. This misuses the service and cannot produce the descriptive sentences the news site needs for accessibility.
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
One of 761 original AI-102 practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. 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.