AI-102 Implement computer vision solutions Practice Question
A developer is building an Azure AI Vision solution that must detect and locate multiple objects in an image, such as cars, people, and traffic lights. The solution must return bounding boxes for each detected object. Which Azure AI Vision capability should the developer use?
⚠ Common exam trap
A common mix-up: candidates confuse object detection with image classification, where classification only labels the overall image and does not provide bounding boxes for individual objects.
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 capability because it identifies and localizes multiple objects in an image, returning bounding boxes and labels for each. Image classification only labels the whole image, OCR extracts text, and face detection is limited to faces. For detecting cars, people, and traffic lights with bounding boxes, object detection is the appropriate Azure AI Vision feature.
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 labels to an entire image but does not provide bounding boxes or locate objects within the image. It cannot tell you where the cars, people, or traffic lights are, only that they might be present. Since the requirement includes bounding boxes for each object, classification alone is insufficient.
- ✓
Object detection
Why this is correct
Object detection in Azure AI Vision identifies and localizes multiple objects within an image, returning bounding boxes and labels for each detected object. It is designed for scenarios like detecting cars, people, and traffic lights simultaneously. This capability directly provides the required bounding box coordinates and object labels, making it the correct choice for the scenario.
- ✗
Optical character recognition (OCR)
Why it's wrong here
OCR extracts text from images and returns text lines and words with their bounding boxes, but it does not detect general objects like cars or people. It is specialized for reading text, not for localizing arbitrary objects. Using OCR would not provide the object detection and bounding boxes needed for cars, people, and traffic lights.
- ✗
Face detection
Why it's wrong here
Face detection locates human faces and returns bounding boxes for them, but it does not detect other objects such as cars or traffic lights. It is a specialized capability within Azure AI Face, not a general object detection service. Since the scenario requires detecting multiple object types, face detection alone cannot satisfy the requirement.
Go deeper
Related to this question
About these practice questions
One of 761 original AI-102 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 →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official Microsoft exam blueprint
This AI-102 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-102 exam.