AI-900 Practice Question: Describe features of computer vision workloads on Azure
A museum wants to create an interactive exhibit where visitors can take a photo of a painting. The system should then generate a descriptive caption (e.g., 'A woman with a pearl earring') and classify the painting as either a portrait or landscape. Which Azure Computer Vision capability should they use without needing to train a custom model?
⚠ Common exam trap
Watch out — candidates often confuse Custom Vision (which requires training) with Image Analysis (which is pre-built), or mistakenly think Face Detection or OCR can generate descriptive captions, when in fact they are specialized for different tasks.
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 Analysis
Image Analysis in Azure Computer Vision provides pre-built capabilities for extracting rich information from images, including generating human-readable captions (via the 'describe' operation) and classifying images into categories like 'portrait' or 'landscape' without requiring any custom training. This directly matches the museum's need for both caption generation and orientation classification using a pre-trained model.
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
Why it's wrong here
Custom Vision enables you to build a bespoke image classifier or object detector by uploading labeled example images and running a training loop. This scenario explicitly asks for a prebuilt capability, so choosing Custom Vision would require creating and managing a custom model, collecting labeled data, and maintaining it—something the museum doesn't want. Although Custom Vision could theoretically classify artworks after training, it is not a zero-training prebuilt solution and thus is inappropriate here.
When this WOULD be correct
Custom Vision would be correct if the museum needed to classify paintings into custom categories (e.g., by artist or period) that are not covered by Azure's pre-built models, and they are willing to train a model with their own labeled images.
- ✓
Image Analysis
Why this is correct
Azure Image Analysis, part of Azure AI Vision, is a prebuilt service that can generate natural-language descriptions of visual content and assign categories such as 'portrait' or 'landscape' without any custom model training. For a museum interactive exhibit, this aligns exactly with the requirement to describe and categorize artworks on the fly. The model also returns tags and confidence scores, letting the exhibit rank possible interpretations and present the most likely caption to visitors.
- ✗
Face Detection
Why it's wrong here
Face Detection is designed to locate human faces in an image and extract attributes like head pose, age, emotion, and facial landmarks. It does not analyze an artwork's composition, genre, or style, so it cannot caption a painting as 'an abstract landscape' or classify its category. Even if a painting contains portraits, Face Detection would return bounding boxes around the faces rather than a description of the artwork as a whole.
When this WOULD be correct
A question asking which Azure service can detect faces in an image, return face rectangles, and optionally analyze attributes like smile or glasses, without needing custom training.
- ✗
Optical Character Recognition (OCR)
Why it's wrong here
Optical Character Recognition (OCR) extracts printed or handwritten text from images and returns the characters along with bounding boxes. The museum's requirement is to describe and classify the visual subject and style of the artwork, not to read any labels or plaques in the image. Therefore OCR would provide only the text layer of an artwork, leaving the actual look and theme unexplored.
When this WOULD be correct
A question asking: 'Which Azure service extracts printed or handwritten text from images, such as reading labels on museum artifacts?' would make OCR correct.
Option-by-option analysis
Why each answer is right or wrong
Understanding why wrong answers are wrong — and when they would be correct — is what separates a 750 score from a 900. The AI-900 exam frequently reuses these exact scenarios with slightly different constraints.
✓Image AnalysisCorrect answer▾
Why this is correct
Azure Image Analysis, part of Azure AI Vision, is a prebuilt service that can generate natural-language descriptions of visual content and assign categories such as 'portrait' or 'landscape' without any custom model training. For a museum interactive exhibit, this aligns exactly with the requirement to describe and categorize artworks on the fly. The model also returns tags and confidence scores, letting the exhibit rank possible interpretations and present the most likely caption to visitors.
✗Custom VisionWrong answer — click to see why▾
Why this is wrong here
Custom Vision requires training a custom model with labeled images, but the question specifies 'without needing to train a custom model.' Image Analysis provides pre-built captioning and classification capabilities out of the box.
★ When this WOULD be the correct answer
Custom Vision would be correct if the museum needed to classify paintings into custom categories (e.g., by artist or period) that are not covered by Azure's pre-built models, and they are willing to train a model with their own labeled images.
Why candidates choose this
Candidates may think that generating descriptive captions and classifying paintings requires custom training, not realizing that Azure's Image Analysis already includes pre-trained models for common tasks like captioning and art classification.
✗Face DetectionWrong answer — click to see why▾
Why this is wrong here
Face Detection identifies human faces and their attributes (e.g., age, emotion) but does not generate descriptive captions or classify paintings as portrait/landscape.
★ When this WOULD be the correct answer
A question asking which Azure service can detect faces in an image, return face rectangles, and optionally analyze attributes like smile or glasses, without needing custom training.
Why candidates choose this
Candidates may think 'portrait' implies face detection is needed, but the task requires caption generation and classification, not just face detection.
✗Optical Character Recognition (OCR)Wrong answer — click to see why▾
Why this is wrong here
OCR extracts text from images, not descriptive captions or painting classifications (portrait vs. landscape). The question requires generating captions and classifying art, which OCR cannot do.
★ When this WOULD be the correct answer
A question asking: 'Which Azure service extracts printed or handwritten text from images, such as reading labels on museum artifacts?' would make OCR correct.
Why candidates choose this
Candidates may think OCR can 'read' the painting's content (e.g., title or artist signature) and infer its type, but OCR only extracts text, not visual features or scene understanding.
Analysis generated from the official AI-900blueprint and verified against question context. The “when correct” sections are what AI assistants cite when candidates ask “what’s the difference between these options?”
Go deeper
Related to this question
Learn chapter
Regression and Classification
Key term
Computer vision
Computer vision is a field of artificial intelligence that enables computers to interpret and make decisions based on visual data from the world, such as images and videos.
Key term
Classification
Classification is a supervised machine learning technique used to predict a category or class label for new data based on patterns learned from labeled training data.
About these practice questions
This AI-900 question is part of Courseiva's 985-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam dumps. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This AI-900 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-900 exam.