A university archives handwritten lecture notes as images. They want to convert these notes into searchable digital text using Azure AI Foundry. Which Azure AI Vision capability should they use?

Image analysis with visualFeatures=['description']

A legal firm needs to extract text from scanned contracts stored as image files. They use Azure AI Foundry to build a solution. Which Azure AI Vision capability should they use in Foundry Tools?

Optical character recognition (OCR)

A developer receives an OCR response with a line of text 'Order #12345' and a confidence score of 0.45. The developer also receives an object detection response with a bounding box for a 'package' with confidence 0.95. What should the developer do to ensure accurate order number extraction?

Ignore the OCR result and use the object detection tag as the order number.

Accept the order number as correct because the package was detected with high confidence.

Increase the confidence threshold in the OCR API request.

Re-run OCR on the cropped region of the bounding box to improve confidence.

A logistics company uses Azure AI Vision to extract tracking numbers from shipping label images. They need to extract text accurately and also know the confidence of the extraction. Which response field should they examine?

The 'confidence' field within each text line or word in the OCR response.

The 'metadata' field containing image dimensions.

After calling the Azure AI Vision Analyze Image API with the Tags feature, a developer receives a JSON response. What does the 'confidence' field in each tag object represent?

The pixel area covered by the tag's bounding box

The number of times the tag appears in the image

The version of the model that generated the tag

The probability that the tag correctly describes the image

Microsoft Certified:Azure AI Engineer Associate

Domain 4Objective 1

Analyze Images AI-102 Practice Questions (Page 2)

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 6–10

6application · easy
A university archives handwritten lecture notes as images. They want to convert these notes into searchable digital text using Azure AI Foundry. Which Azure AI Vision capability should they use?
Select an answer first
7application · easy
A legal firm needs to extract text from scanned contracts stored as image files. They use Azure AI Foundry to build a solution. Which Azure AI Vision capability should they use in Foundry Tools?
Select an answer first
8expert · hard
A developer receives an OCR response with a line of text 'Order #12345' and a confidence score of 0.45. The developer also receives an object detection response with a bounding box for a 'package' with confidence 0.95. What should the developer do to ensure accurate order number extraction?
Select an answer first
9application · medium
A logistics company uses Azure AI Vision to extract tracking numbers from shipping label images. They need to extract text accurately and also know the confidence of the extraction. Which response field should they examine?
Select an answer first
10foundation · easy
After calling the Azure AI Vision Analyze Image API with the Tags feature, a developer receives a JSON response. What does the 'confidence' field in each tag object represent?
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.