AI-900 Practice Question: Describe features of computer vision workloads on Azure
A retail company wants to use Azure Computer Vision to automatically monitor shelf inventory. They need to detect whether items are present on a shelf and count the number of items, without needing to identify the specific product type. Which prebuilt Computer Vision capability should they use?
⚠ Common exam trap
Many candidates confuse object detection with image classification, assuming that classifying the shelf as 'stocked' or 'empty' is sufficient, but the question explicitly requires counting individual items, which only object detection can provide.
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 (Option C) is the correct prebuilt Computer Vision capability because it can both locate items within an image using bounding boxes and count them, without requiring identification of the specific product type. This aligns directly with the requirement to detect presence and count items on a shelf, as object detection outputs the coordinates and count of detected objects, not their classification into fine-grained categories.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Optical Character Recognition (OCR)
Why it's wrong here
Optical Character Recognition (OCR) is designed only to extract printed or handwritten text characters from images, mapping them to machine-encoded strings. Retail items like cans or boxes without visible text, or products with graphics, would not be detected as objects. OCR cannot identify, localize, or count general non-text items, so it is unrelated to the requirement of counting items on a shelf.
When this WOULD be correct
A question where the goal is to read product labels, expiration dates, or barcodes from shelf items to track inventory by text.
- ✗
Image classification
Why it's wrong here
Image classification assigns a single, global label to the entire image, such as 'shelf with items', without localizing objects. It cannot distinguish multiple instances of the same class or provide their positions, so it has no mechanism for counting individual products. Since the retail use case requires counting items, a whole-image label is insufficient to answer the question.
- ✓
Object detection
Why this is correct
Object detection is the correct approach because it identifies each object instance within an image and returns a bounding box and confidence score for every detection. By counting the number of bounding boxes returned—even when all detections share the same class label (e.g., 'product')—you can accurately count items on a shelf. Azure Computer Vision's prebuilt object detection API is specifically designed for this scenario, providing both count and spatial location for each item.
- ✗
Semantic segmentation
Why it's wrong here
Semantic segmentation labels every pixel in the image with a class (such as 'item' or 'shelf'), but it does not distinguish between separate instances of the same class. Two adjacent products on a shelf would be merged into one contiguous 'item' region, making individual counting impossible. Azure Computer Vision does not offer a prebuilt semantic segmentation service, and even with custom models, instance segmentation (not semantic segmentation) would be needed for accurate object counting.
When this WOULD be correct
A question that requires precise measurement of shelf space occupancy or identifying the exact shape and boundaries of items for inventory layout optimization would make semantic segmentation the correct choice, such as 'Which Computer Vision capability should be used to calculate the percentage of shelf space occupied by products?'
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 detectionCorrect answer▾
Why this is correct
Object detection is the correct approach because it identifies each object instance within an image and returns a bounding box and confidence score for every detection. By counting the number of bounding boxes returned—even when all detections share the same class label (e.g., 'product')—you can accurately count items on a shelf. Azure Computer Vision's prebuilt object detection API is specifically designed for this scenario, providing both count and spatial location for each item.
✗Optical Character Recognition (OCR)Wrong answer — click to see why▾
Why this is wrong here
OCR extracts text from images, but the question requires detecting and counting items on a shelf without identifying product type, which is not text-based.
★ When this WOULD be the correct answer
A question where the goal is to read product labels, expiration dates, or barcodes from shelf items to track inventory by text.
Why candidates choose this
Candidates may confuse inventory monitoring with reading product labels, assuming OCR is needed to identify items.
✗Semantic segmentationWrong answer — click to see why▾
Why this is wrong here
Semantic segmentation assigns a class label to every pixel in an image, which is overkill for simply detecting and counting items on a shelf; object detection is more efficient for identifying and localizing individual items without needing pixel-level precision.
★ When this WOULD be the correct answer
A question that requires precise measurement of shelf space occupancy or identifying the exact shape and boundaries of items for inventory layout optimization would make semantic segmentation the correct choice, such as 'Which Computer Vision capability should be used to calculate the percentage of shelf space occupied by products?'
Why candidates choose this
Candidates may confuse semantic segmentation with object detection because both involve identifying objects, but segmentation's pixel-level detail seems more 'precise' for counting, even though it's unnecessary for simple item detection and counting.
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
Inventory
Inventory is the complete list of hardware, software, and network assets that an organization owns or manages, tracked for maintenance, security, and budgeting purposes.
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
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.