AI-900 Practice Question: Describe features of computer vision workloads on Azure
A warehouse uses AI to monitor inventory. They need to detect the presence and location of specific objects (e.g., forklifts, pallets) in real-time video feeds. Which Azure Computer Vision capability should they use?
⚠ Common exam trap
Many exam-takers confuse image classification (which only labels the whole scene) with object detection (which locates individual objects), especially when the question emphasizes 'presence and location' — a classic AI-900 pitfall.
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 choice because it identifies specific objects (e.g., forklifts, pallets) within an image or video frame and returns bounding box coordinates indicating their location. This capability is designed for real-time spatial awareness, which directly matches the warehouse's need to detect both the presence and position of objects in video 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 classification
Why it's wrong here
Assigns a single label to the entire image, outputting a class such as 'warehouse' or 'empty'. It processes the image as a whole and does not localize or count multiple objects; for a monitoring task that needs to identify where forklifts and pallets are positioned, classification lacks spatial awareness and cannot return bounding boxes or per-object labels. Therefore it cannot satisfy the requirement to detect and locate individual inventory items.
- ✗
OCR (optical character recognition)
Why it's wrong here
Optical character recognition is designed to extract machine-printed or handwritten text from images, converting it into machine-readable characters. Warehouse inventory monitoring typically requires detecting physical objects like pallets and forklifts, which have no textual content, so OCR would fail to identify their presence or positions. Unless the system relies on reading labels or barcode numbers (not object detection), OCR is irrelevant.
- ✓
Object detection
Why this is correct
Object detection combines classification and localization, scanning an image to find multiple instances of known classes and outputting a bounding box plus class label for each. In a warehouse scenario, it can simultaneously detect forklifts, pallets, and shelves, providing the coordinates needed to monitor inventory movement and count items. This directly supports the requirement to 'detect' items in a way that image classification alone cannot.
- ✗
Facial recognition
Why it's wrong here
Facial recognition maps and compares facial features of human faces, typically using embeddings to identify specific individuals. Warehouse inventory objects such as forklifts and pallets have no facial geometry, so this specialized biometric technique is not applicable. It cannot detect or classify non-human objects, making it unsuitable for inventory monitoring.
Go deeper
Related to this question
Learn chapter
Azure Machine Learning Studio
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
Object detection
Object detection is a computer vision technology that identifies and locates specific objects within an image or video.
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.