AI-900 Practice Question: Describe features of computer vision workloads on Azure
A logistics warehouse uses a conveyor belt system to move packages. They need to automatically read the alphanumeric serial numbers printed on labels attached to each box. The labels may have different fonts and be somewhat dusty. Which Azure Computer Vision feature should they use?
⚠ Common exam trap
Test-takers frequently confuse Object Detection (finding objects) with OCR (reading text), or assume Image Classification can handle text extraction, when in fact only the Read API is designed for text recognition under challenging conditions.
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
✓
Optical Character Recognition (OCR) using the Read API
The Read API, part of Azure Computer Vision's OCR capabilities, is specifically designed to extract printed and handwritten text from images, including alphanumeric serial numbers. It can handle varying fonts and degraded image quality (e.g., dusty labels) by using deep-learning models optimized for text recognition. This makes it the correct choice for reading serial numbers from conveyor belt packages.
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
Image classification assigns one or more pre-defined class labels to an entire image, such as 'cardboard box on conveyor belt' or 'labeled package', but it does not inspect the individual pixels that form each character. It uses a trained model that scores the image against a set of categories, and the output is only the category name and confidence score. Consequently, even if the model correctly recognizes that the image shows a labeled box, it cannot produce the exact serial number string from that label.
When this WOULD be correct
A question asking to categorize images of packages into types (e.g., 'fragile', 'electronics') based on visual features, without needing to read text.
- ✓
Optical Character Recognition (OCR) using the Read API
Why this is correct
The Azure AI Vision Read API performs OCR by detecting and extracting text from images, converting handwritten or printed characters into machine-readable strings. In this warehouse conveyor scenario, each serial number on a box label can be captured by a camera and transcribed into an alphanumeric value exactly as printed, even under uneven lighting, slight rotation, or varied label fonts. Because the goal is to record a specific identifier rather than categorize or describe the box, OCR is the only service that directly returns the serial number itself.
- ✗
Object Detection
Why it's wrong here
Object detection returns the locations of objects in an image by drawing bounding boxes around recognized entities and outputting the object class, along with confidence scores. While it could find the box or even the label as an object, its output consists of coordinates and class names ('box', 'label'), not the textual characters inside those boxes. It cannot decode the OCR-like glyphs in the serial number, so it is unsuitable for extracting the identifier.
When this WOULD be correct
A warehouse needs to count the number of boxes on a conveyor belt and determine their positions. Object Detection would be correct because it can detect and locate each box in the image.
- ✗
Image Analysis (captioning and tagging)
Why it's wrong here
Image Analysis with captioning and tagging generates human-friendly descriptions of the image and returns semantic tags such as 'box', 'text', 'conveyor belt', and 'warehouse', rather than the discrete characters printed on the label. Captioning produces a single-sentence summary like 'a cardboard box on a conveyor belt' and is designed for accessibility or search, not for character-level transcription. This option fails the requirement because it never segments the label into letters and digits, so it cannot supply the exact serial number needed for inventory tracking.
When this WOULD be correct
A question asking for generating a human-readable description of a scene or identifying objects/attributes (e.g., 'What objects are in this warehouse image?') would make Image Analysis correct.
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.
✓Optical Character Recognition (OCR) using the Read APICorrect answer▾
Why this is correct
The Azure AI Vision Read API performs OCR by detecting and extracting text from images, converting handwritten or printed characters into machine-readable strings. In this warehouse conveyor scenario, each serial number on a box label can be captured by a camera and transcribed into an alphanumeric value exactly as printed, even under uneven lighting, slight rotation, or varied label fonts. Because the goal is to record a specific identifier rather than categorize or describe the box, OCR is the only service that directly returns the serial number itself.
✗Image ClassificationWrong answer — click to see why▾
Why this is wrong here
Image Classification categorizes the entire image into predefined classes (e.g., 'box', 'label'), but cannot extract specific alphanumeric text from labels, especially with varied fonts and dust.
★ When this WOULD be the correct answer
A question asking to categorize images of packages into types (e.g., 'fragile', 'electronics') based on visual features, without needing to read text.
Why candidates choose this
Candidates may confuse 'reading text' with 'classifying images', thinking that recognizing serial numbers is a classification task rather than a text extraction task.
✗Object DetectionWrong answer — click to see why▾
Why this is wrong here
Object Detection identifies and locates objects (e.g., boxes, people) in an image, but it cannot read alphanumeric text. The requirement is to read serial numbers, which requires OCR, not object detection.
★ When this WOULD be the correct answer
A warehouse needs to count the number of boxes on a conveyor belt and determine their positions. Object Detection would be correct because it can detect and locate each box in the image.
Why candidates choose this
Candidates may confuse 'detecting' objects with 'reading' text on objects, assuming Object Detection can extract text from labels, but it only provides bounding boxes and object classes, not character recognition.
✗Image Analysis (captioning and tagging)Wrong answer — click to see why▾
Why this is wrong here
Image Analysis (captioning and tagging) generates descriptive labels and captions for images, but it cannot extract specific alphanumeric serial numbers from labels, especially with varied fonts and dust.
★ When this WOULD be the correct answer
A question asking for generating a human-readable description of a scene or identifying objects/attributes (e.g., 'What objects are in this warehouse image?') would make Image Analysis correct.
Why candidates choose this
Candidates may think 'Image Analysis' includes all computer vision tasks, including text extraction, or they confuse tagging with OCR capabilities.
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
Machine Learning Core Concepts
Key term
OCR
Optical Character Recognition is technology that converts images of text, like scanned documents or photos, into machine-readable text data.
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
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.