A legal firm needs to digitize scanned contracts. The scans contain printed text in multiple languages. They want to extract the text and also get the bounding boxes for each line of text so they can map the text to form fields. Which Azure AI Vision capability should they use?

Image Analysis with Description

When using Azure AI Vision OCR to process an image containing handwritten text, what should a developer expect in the response?

The handwritten text is returned as recognized text with confidence scores

The response includes a list of objects detected in the image

The response contains only a generic description of the handwriting style

The response indicates that handwriting is not supported

A developer is using Azure AI Vision to analyze images of food dishes. The API returns a JSON response. They need to extract the confidence score for the 'pizza' tag to decide whether to display the tag to users. Which part of the response should they inspect?

The 'description' object and its 'captions' array

The 'tags' array and the 'confidence' property of each tag object

An application uses Azure AI Vision to generate relevant tags for an image. Which API or feature should be used to obtain a list of words that describe the image content?

The Tags visual feature in the Analyze Image API

Microsoft Certified:Azure AI Engineer Associate

Domain 4Objective 1

Analyze Images AI-102 Practice Questions (Page 3)

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 11–15

11application · medium
A legal firm needs to digitize scanned contracts. The scans contain printed text in multiple languages. They want to extract the text and also get the bounding boxes for each line of text so they can map the text to form fields. Which Azure AI Vision capability should they use?
Select an answer first
12foundation · easy
When using Azure AI Vision OCR to process an image containing handwritten text, what should a developer expect in the response?
Select an answer first
13application · medium
A developer is using Azure AI Vision to analyze images of food dishes. The API returns a JSON response. They need to extract the confidence score for the 'pizza' tag to decide whether to display the tag to users. Which part of the response should they inspect?
Select an answer first
14foundation · easy
A developer is using Azure AI Vision to analyze a photo of a city street. They need to obtain a list of objects detected in the image, along with their bounding boxes. Which visual feature should they request?
Select an answer first
15foundation · easy
An application uses Azure AI Vision to generate relevant tags for an image. Which API or feature should be used to obtain a list of words that describe the image content?
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.