Courseiva

AI-900 Practice Question: Describe features of computer vision workloads on Azure

A retail chain wants to automatically detect which specific products are missing from store shelves by analyzing images from in-store cameras. Each product has a distinct shape and label. Which Azure Computer Vision capability is most appropriate for this task?

⚠ Common exam trap

Many candidates confuse Image Classification with Object Detection, thinking that classifying the entire image as 'shelf with products' is sufficient, but the task requires locating and identifying individual missing products, which only Object Detection can do.

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

B) Object Detection

Object Detection (Option B) is the correct choice because it can identify and locate multiple products within an image by drawing bounding boxes around each detected object. This allows the system to determine which specific products are missing by comparing detected items against an expected inventory list. Image Classification would only label the entire image, not individual products, while OCR focuses on text extraction and Facial Recognition identifies people.

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

  • A) Image Classification

    Why it's wrong here

    Image classification assigns a single categorical label to the entire input image using a model such as a convolutional neural network with a softmax output. It produces no bounding boxes or instance counts, so in a retail shelf scene it cannot distinguish one product from another or identify which specific SKUs are missing. At most, it could label the whole scene as e.g. 'stocked shelf' or 'empty shelf'.

  • B) Object Detection

    Why this is correct

    Object detection both localizes and classifies each object in an image by outputting bounding boxes and class labels for every detected instance. Architectures like Faster R-CNN or YOLO generate region proposals or grid-based predictions, allowing the system to count and identify each product on a shelf. By comparing the detected products against an expected planogram, the system can pinpoint exactly which specific items are absent.

  • C) Optical Character Recognition (OCR)

    Why it's wrong here

    OCR converts images of text into machine-readable character strings, using techniques like text detection, character segmentation, and recognition. It can read a product label or barcode only if visible text is present and legible, but it provides no geometric or semantic understanding of the physical product itself. If a can or bottle is present yet its label is rotated, obscured, or absent, OCR cannot determine whether that product is on the shelf.

  • D) Facial Recognition

    Why it's wrong here

    Facial recognition is a specialized biometric task that detects human faces, extracts face embeddings, and matches them against a known gallery of identities. Its models are trained on facial features and are not designed to represent arbitrary product packaging or distinguish different retail SKUs. Applying facial recognition to a shelf image would fail because it lacks the category space and localization structure needed to identify products, let alone missing items.

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 →

How Courseiva writes practice questions · Editorial policy

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.