AI-900 Practice Question: Describe features of computer vision workloads on Azure
A logistics company processes packages on an automated conveyor belt. They need to read shipping labels that are often rotated or skewed, and also detect whether a 'FRAGILE' sticker is present on the package. Which combination of Azure Computer Vision capabilities should they use?
⚠ Common exam trap
It's easy for candidates to confuse Image Classification (which labels the whole image) with Object Detection (which finds specific objects), leading them to pick Option B, thinking classification can detect a sticker, when it cannot provide location or multiple object instances.
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
✓
OCR (Read API) and Object Detection
The scenario requires reading rotated or skewed text from shipping labels (handled by the OCR Read API, which extracts printed and handwritten text from images, even when rotated or skewed) and detecting whether a 'FRAGILE' sticker is present (handled by Object Detection, which identifies and locates specific objects—like stickers—within an image). Option A correctly pairs these two capabilities to meet both requirements.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
OCR (Read API) and Object Detection
Why this is correct
This combination directly satisfies both requirements in the scenario: the OCR Read API extracts text from package labels even when the text is rotated or skewed on the conveyor, while Object Detection identifies and localizes specific objects such as a 'FRAGILE' sticker by returning its bounding box coordinates. Together, these capabilities allow the automated system to both read the label content and confirm the presence/position of the sticker, enabling correct downstream routing or handling decisions.
- ✗
Image Classification and OCR (Read API)
Why it's wrong here
Image Classification assigns a single class label to the entire image (e.g., 'package') and provides no spatial information, so it cannot indicate where a 'FRAGILE' sticker is located or even reliably distinguish it from other package elements when multiple objects appear. OCR (Read API) does extract text from rotated labels, but without Object Detection there is no localized anchor for the sticker itself, meaning the combination still fails to deliver the location data essential for automated package handling.
- ✗
Object Detection and Face Detection
Why it's wrong here
Object Detection can locate a 'FRAGILE' sticker in the image, but Face Detection is purpose-built to find and analyze human faces, which is irrelevant to reading package labels or identifying stickers. The scenario also requires OCR to extract text from the label, and since Face Detection provides neither text extraction nor general object localization, this pairing leaves the conveyor system unable to process the label's content or determine the sticker's exact position.
- ✗
Image Classification and Face Detection
Why it's wrong here
Image Classification can only output a broad label for the whole scene, such as 'package on conveyor', without any ability to locate individual elements, and Face Detection is exclusively tuned for human facial features, making it useless for reading labels or detecting stickers. Neither capability performs OCR (text extraction from rotated text) nor Object Detection (localizing a 'FRAGILE' sticker), so the combination ignores the two core needs of the scenario and cannot support automated package decision-making.
Go deeper
Related to this question
Learn chapter
Azure Machine Learning Studio
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
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.