AI-900 Practice Question: Describe features of computer vision workloads on Azure
What information does Azure AI Face service provide about detected faces beyond just their location?
⚠ Common exam trap
A common mix-up: candidates assume the Face service only provides basic location data (bounding box) or mistakenly think it can look up identities from public databases like social media, when in fact it requires custom enrollment for identification.
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
✓
Age estimate, emotion, head pose, and other facial attributes
Azure AI Face service can extract a wide range of facial attributes beyond just the bounding box coordinates. These include age estimate, emotion (e.g., happiness, sadness, surprise), head pose (pitch, yaw, roll), facial hair, glasses, and more, making option B correct.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Only the coordinates of the face bounding box
Why it's wrong here
Although the core detect operation does return an axis-aligned bounding box (faceId, left, top, width, height), that is only the default, low-level output. The same API supports optional parameters such as returnFaceLandmarks (27 landmark points) and returnFaceAttributes (age, glasses, emotion, head pose), and the service layer extends to identification against private person groups. In practice, many Azure Face scenarios—like access control or user engagement analysis—rely on those rich attributes rather than the bare rectangle. Limiting the answer to bounding box ignores the rest of the AI capability.
- ✓
Age estimate, emotion, head pose, and other facial attributes
Why this is correct
Azure AI Face, when called with the returnFaceAttributes parameter, delivers a compact face rectangle plus rich derived attributes: an estimated age range (not a verified birth date), a weighted emotion vector (anger, sadness, surprise, etc.), head pose angles (pitch, yaw, roll), and additional signals such as glasses, facial hair, and blur. These attributes come from deep neural networks trained on large face datasets, and they are probabilistic—so age and emotion are inferred, not measured precisely. The service returns these alongside the detected face location, giving developers more than just a raw crop.
- ✗
The person's name and identity from a public database
Why it's wrong here
Face identification is strictly private-enrollment based: you must pre-create a PersonGroup, add reference photos of known persons, and run the Train operation before any identification call. At runtime, the Face service compares the detected face descriptor (a 128-dimensional vector) only to those enrolled identities, returning a Person ID and confidence score. It never consults public databases, social media profiles, or government records, and Microsoft's Responsible AI usage limits prohibit building an unrestricted public face-matching database without explicit approval.
- ✗
Only whether the face belongs to a human or not
Why it's wrong here
The Face service never attempts to classify whether a detected face is human versus non-human—it assumes the input contains human faces and focuses on localizing them and extracting attributes. In fact, the service may return face candidates even for non-human objects with a face-like structure, though it is designed for human faces. The purpose is not a binary 'human or not' check; it can identify faces, analyze attributes, and estimate pose, so reducing it to that boolean defeats the API's actual capability. If the input is not a human face, the detection simply returns an empty list.
Go deeper
Related to this question
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 →
Same concept, more angles
1 more way this is tested on AI-900
These questions test the same concept from different angles. Work through them to make sure you can recognise it however the exam phrases it.
Variation 1. What is 'face attribute analysis' in Azure AI Face service?
medium- A.Identifying the named person in a photograph using a face database
- ✓ B.Estimating age, emotion, head pose, and appearance attributes from detected faces
- C.Verifying whether a submitted selfie matches a government-issued ID document
- D.Detecting whether a face has been digitally manipulated or deepfaked
Why B: Face attribute analysis in Azure AI Face service extracts a set of facial attributes from detected faces, including estimated age, emotion (e.g., happiness, sadness, anger), head pose (pitch, yaw, roll), and appearance traits like facial hair, glasses, and makeup. This is distinct from identification or verification tasks because it does not match faces against a database or compare two images; it simply returns metadata about the face itself.
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.