AI-900 Practice Question: Describe features of computer vision workloads on Azure
A retail company uses security cameras to monitor shelves. They want to identify whether a customer is holding a specific product (e.g., a green detergent bottle) and also determine the location of that product within the camera frame. Which Azure Computer Vision capability should they use?
⚠ Common exam trap
Candidates often confuse object detection with image classification, thinking that identifying the product is sufficient, but they overlook the explicit requirement for location information that only object detection provides.
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
Object detection is the correct capability because it not only identifies the presence of a specific product (like a green detergent bottle) in an image but also returns bounding box coordinates that indicate the product's location within the camera frame. This dual output—classification plus localization—directly matches the requirement to both recognize the object and determine its position.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Object detection
Why this is correct
Object detection is the correct choice because it localizes each product instance with a bounding box and assigns a class label, giving both the identity and XY coordinates of every detected object. This allows the system to count items on shelves, identify empty spaces, and even track stock levels over time. The output is ideal for downstream analytics such as triggering reorders or detecting displacement, which directly matches the retail monitoring requirement.
- ✗
Image classification
Why it's wrong here
Image classification assigns a single class label to the entire image as a whole, such as 'shelf' or 'full_shelf', with no ability to output any spatial coordinates. It cannot distinguish multiple objects within the scene, nor can it tell where a specific product is located, which is exactly what shelf monitoring requires. Even with a multi-label variant, classification still lacks the localization map that bounding-box regression provides, so it fails to meet the core need.
- ✗
Optical character recognition (OCR)
Why it's wrong here
Optical character recognition (OCR) specifically extracts alphanumeric characters from text regions, using techniques like text detection and character segmentation, and outputs the recognized string. While OCR could read product labels or prices on shelf tags, it cannot detect non-textual objects like a shampoo bottle or a cereal box by their visual shape or texture. Moreover, even when labels exist, OCR does not provide a semantic understanding of the object itself, so it is fundamentally misaligned with the goal of identifying and locating products.
- ✗
Semantic segmentation
Why it's wrong here
Semantic segmentation classifies every pixel into a predefined class, producing a pixel-level mask (e.g., all 'boxes' pixels in one class) but without distinguishing between distinct instances of the same class. This means two adjacent identical products merge into a single contiguous blob, so you cannot count individual units or draw per-item bounding boxes for shelf monitoring. The lack of instance separation makes it poorly suited for tasks that require accurate localization and counting of individual objects, unlike object detection.
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
Object detection
Object detection is a computer vision technology that identifies and locates specific objects within an image or video.
About these practice questions
Courseiva writes every AI-900 question from scratch — 985 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or 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.