A developer wants to analyze an image using Azure AI Vision and retrieve both tags and a description in a single API call. How should the request be constructed?

Make two separate calls: one for Tags and one for Description

Use the OCR API for tags and the Face API for description

Set the visualFeatures parameter to 'Tags, Description'

Set the language parameter to 'Tags, Description'

A developer calls the Analyze Image API with visualFeatures=['objects'] and receives a response with an 'objects' array containing two entries. What does this indicate?

The API failed to analyze the image.

The image is a duplicate of another image.

The image contains exactly two objects and nothing else.

The API detected two objects in the image.

A user in Microsoft Foundry needs to extract printed text from an image of a receipt. Which Azure AI Vision capability should they use?

OCR (Optical Character Recognition)

A user in Microsoft Foundry needs to convert a photo of a handwritten note into digital text. Which Azure AI Vision capability is designed for this task?

OCR (Optical Character Recognition)

A developer calls the Azure AI Vision Analyze Image API with the visualFeatures parameter set to 'Objects'. What will the response include for each detected object?

A caption and a confidence score

A bounding box and a confidence score

Microsoft Certified:Azure AI Engineer Associate

Domain 4Objective 1

Analyze Images AI-102 Practice Questions (Page 4)

Part of the Implement computer vision solutions domain, which accounts for 10-15% of the AI-102 exam. Microsoft does not publish an official question count, but from its 100-minute exam (~40–65 total, ~4–10 in this domain), expect 1–3 from this objective — we provide 24 practice questions to prepare you well beyond it. (estimate)

24questions here

5free pages

6concepts

10-15%of the exam

Questions 16–20

16foundation · easy
A developer wants to analyze an image using Azure AI Vision and retrieve both tags and a description in a single API call. How should the request be constructed?
Select an answer first
17application · easy
A developer calls the Analyze Image API with visualFeatures=['objects'] and receives a response with an 'objects' array containing two entries. What does this indicate?
Select an answer first
18foundation · easy
A user in Microsoft Foundry needs to extract printed text from an image of a receipt. Which Azure AI Vision capability should they use?
Select an answer first
19foundation · easy
A user in Microsoft Foundry needs to convert a photo of a handwritten note into digital text. Which Azure AI Vision capability is designed for this task?
Select an answer first
20foundation · easy
A developer calls the Azure AI Vision Analyze Image API with the visualFeatures parameter set to 'Objects'. What will the response include for each detected object?
Select an answer first

Finished these 5 questions?

Review the revealed explanations, or continue through the curriculum.

Next 5 questions →Back to AI-102

Free Basic Practice is a study aid with revealable answers — not a scored exam. Examers.io is independent and not affiliated with or endorsed by Microsoft. “AI-102” is a trademark of its owner, used for identification only.