AI-900 Practice Question: Describe features of computer vision workloads on Azure
A city traffic department wants to use Azure Computer Vision to automatically analyze live video feeds from traffic cameras. They need to detect and locate common objects such as cars, pedestrians, and bicycles in each frame. The department does not have a labeled dataset for custom training. Which prebuilt Azure Computer Vision capability should they use?
⚠ Common exam trap
It's easy for candidates to confuse 'descriptive tags' (Option A) with object detection, not realizing that tags only describe the scene without providing spatial location, which is essential for the 'locate' requirement in the question.
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
✓
Object Detection (part of Image Analysis 4.0)
The Object Detection capability within Image Analysis 4.0 can detect and locate common objects (e.g., cars, pedestrians, bicycles) in images or video frames without requiring any labeled dataset. It provides bounding box coordinates for each detected object, which directly meets the requirement to 'detect and locate' objects in live traffic camera feeds.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Image Analysis (descriptive tags and captions)
Why it's wrong here
Image Analysis descriptive tags and captions can identify that a scene contains a car or pedestrian, but they return only a label or natural-language sentence, not a spatial location. The department needs to know where objects are, which requires bounding boxes, a capability that belongs to the Object Detection API rather than tagging or captioning.
When this WOULD be correct
If the traffic department only needed to generate a list of objects present in each frame (e.g., 'car, pedestrian, bicycle') without needing their positions, Image Analysis descriptive tags would be the correct choice.
- ✗
Optical Character Recognition (OCR) API
Why it's wrong here
The OCR API is built specifically to extract printed and handwritten text from images, returning text content and polygon coordinates of text regions. It is a text-extraction service, so it has no model for recognizing cars, pedestrians, or bicycles, making it fundamentally wrong for object detection.
When this WOULD be correct
A company needs to extract license plate numbers from traffic camera images to identify vehicles. They would use OCR to read the alphanumeric text on plates.
- ✓
Object Detection (part of Image Analysis 4.0)
Why this is correct
Object Detection in Image Analysis 4.0 is a prebuilt Azure AI Vision capability that returns bounding-box coordinates and confidence scores for common objects such as cars, people, and bicycles, all without any custom training. Since the traffic department only needs to locate known objects in street imagery, this API directly satisfies the requirement.
- ✗
Custom Vision object detection
Why it's wrong here
Custom Vision object detection would force the department to build and label a dataset of traffic images, then train and publish a custom model before it can detect anything. Because the requirement is to use a ready-made Azure Computer Vision service with no labeled dataset, this option adds unnecessary work and is therefore not the right prebuilt solution.
When this WOULD be correct
A company has a large labeled dataset of specific objects (e.g., rare bird species) and needs to detect only those objects in images. Custom Vision object detection would be correct because it allows training a custom model on their own dataset.
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.
✓Object Detection (part of Image Analysis 4.0)Correct answer▾
Why this is correct
Object Detection in Image Analysis 4.0 is a prebuilt Azure AI Vision capability that returns bounding-box coordinates and confidence scores for common objects such as cars, people, and bicycles, all without any custom training. Since the traffic department only needs to locate known objects in street imagery, this API directly satisfies the requirement.
✗Image Analysis (descriptive tags and captions)Wrong answer — click to see why▾
Why this is wrong here
Image Analysis with descriptive tags and captions identifies objects and scenes but does not provide bounding box coordinates to locate objects within the frame, which is required for detecting and locating cars, pedestrians, and bicycles.
★ When this WOULD be the correct answer
If the traffic department only needed to generate a list of objects present in each frame (e.g., 'car, pedestrian, bicycle') without needing their positions, Image Analysis descriptive tags would be the correct choice.
Why candidates choose this
Candidates may confuse general image description with object detection, assuming that 'tags and captions' include location information, or they may not be aware that Image Analysis 4.0 offers a dedicated object detection feature.
✗Optical Character Recognition (OCR) APIWrong answer — click to see why▾
Why this is wrong here
The OCR API extracts text from images, not objects like cars or pedestrians. The question requires detecting and locating objects, not reading text.
★ When this WOULD be the correct answer
A company needs to extract license plate numbers from traffic camera images to identify vehicles. They would use OCR to read the alphanumeric text on plates.
Why candidates choose this
Candidates may confuse OCR with object detection because both analyze images, or they might think traffic cameras primarily read license plates.
✗Custom Vision object detectionWrong answer — click to see why▾
Why this is wrong here
The department lacks a labeled dataset for custom training, so Custom Vision object detection cannot be used without first creating and training a custom model with labeled images.
★ When this WOULD be the correct answer
A company has a large labeled dataset of specific objects (e.g., rare bird species) and needs to detect only those objects in images. Custom Vision object detection would be correct because it allows training a custom model on their own dataset.
Why candidates choose this
Candidates may think 'custom' implies flexibility for any scenario, overlooking the prerequisite of having a labeled dataset for training.
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
Azure Machine Learning Studio
Key term
Object detection
Object detection is a computer vision technology that identifies and locates specific objects within an image or video.
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.
About these practice questions
One of 985 original AI-900 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 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.