AI-900 Practice Question: Describe features of computer vision workloads on Azure
A nature conservation organization wants to create an app that automatically identifies different species of birds from photos uploaded by birdwatchers. They have thousands of labeled images of bird species. Which Azure service should they use to train a custom model?
⚠ Common exam trap
Watch out — candidates often confuse the general-purpose Computer Vision Image Analysis (which cannot be retrained) with Custom Vision (which is specifically designed for custom classification), leading them to pick option A.
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
✓
Azure Custom Vision
Azure Custom Vision is the correct choice because it allows you to train a custom image classification model using your own labeled dataset of bird species. Unlike the pre-built Computer Vision Image Analysis service, Custom Vision specializes in fine-grained classification tasks where you need to distinguish between dozens or hundreds of visually similar categories, such as different bird species.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Azure Computer Vision Image Analysis
Why it's wrong here
Azure Computer Vision Image Analysis is a prebuilt service that automatically generates tags, captions, and detected objects from images, but it cannot be retrained on your own categories. It will likely return a generic 'bird' tag or bounding box, but it has no learned concept of your organization's specific species classes. Without a custom-training capability, it cannot produce reliable species-level identification for a conservation app.
When this WOULD be correct
A company wants to automatically generate captions and detect common objects in general photos without needing custom training. They have no labeled dataset and require a pre-trained service that works out-of-the-box.
- ✓
Azure Custom Vision
Why this is correct
Azure Custom Vision is a dedicated, low-code cognitive service for building your own image classification or object detection models. You upload labeled photos of each bird species, train an iteration, and then call the exported model endpoint from the app to classify new sightings. Because it is purpose-built for custom visual categories, it fits identifying many specific bird species far better than any prebuilt API.
- ✗
Azure Face API
Why it's wrong here
Azure Face API is a specialized service for detecting, identifying, and analyzing human faces, including attributes like age and emotion. It relies on facial landmarks and face-specific algorithms, and it is not a general-purpose image classifier for animal or plant species. Therefore, it cannot be used to recognize birds in a conservation app.
When this WOULD be correct
A company wants to build an app that identifies employees from security camera footage for access control. They have labeled images of employee faces. Azure Face API would be the correct service to train a custom face recognition model.
- ✗
Azure Form Recognizer
Why it's wrong here
Azure Form Recognizer is designed solely for document intelligence: it extracts key-value pairs, tables, and text from forms and invoices using optical character recognition and layout analysis. A photograph of a bird contains no document structure, so this service would only return any visible text or nothing useful. It does not perform any image classification or visual identification of animals, making it completely unsuitable.
When this WOULD be correct
A question asking which service to use for automatically extracting fields (like species name, date, location) from handwritten birdwatching log sheets or field notes would make Form Recognizer the correct answer.
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.
✓Azure Custom VisionCorrect answer▾
Why this is correct
Azure Custom Vision is a dedicated, low-code cognitive service for building your own image classification or object detection models. You upload labeled photos of each bird species, train an iteration, and then call the exported model endpoint from the app to classify new sightings. Because it is purpose-built for custom visual categories, it fits identifying many specific bird species far better than any prebuilt API.
✗Azure Computer Vision Image AnalysisWrong answer — click to see why▾
Why this is wrong here
Azure Computer Vision Image Analysis provides pre-built image analysis capabilities (e.g., object detection, tags) but does not support training custom models with user-provided labeled images for specific bird species.
★ When this WOULD be the correct answer
A company wants to automatically generate captions and detect common objects in general photos without needing custom training. They have no labeled dataset and require a pre-trained service that works out-of-the-box.
Why candidates choose this
Candidates may confuse the general image analysis capabilities of Computer Vision with the custom model training offered by Custom Vision, assuming any Azure image service can be trained on custom data.
✗Azure Face APIWrong answer — click to see why▾
Why this is wrong here
Azure Face API is specialized for detecting, recognizing, and analyzing human faces, not bird species. It cannot be trained to identify different bird species from photos.
★ When this WOULD be the correct answer
A company wants to build an app that identifies employees from security camera footage for access control. They have labeled images of employee faces. Azure Face API would be the correct service to train a custom face recognition model.
Why candidates choose this
Candidates may think 'Face API' can be generalized to any object recognition task, or they confuse it with Custom Vision's ability to train custom classifiers, not realizing Face API is limited to human faces.
✗Azure Form RecognizerWrong answer — click to see why▾
Why this is wrong here
Azure Form Recognizer is designed for extracting text and structure from documents (e.g., invoices, forms), not for classifying bird species from photos.
★ When this WOULD be the correct answer
A question asking which service to use for automatically extracting fields (like species name, date, location) from handwritten birdwatching log sheets or field notes would make Form Recognizer the correct answer.
Why candidates choose this
Candidates may think 'recognizer' implies image recognition, or they confuse document analysis with general image classification.
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
Regression and Classification
Key term
Image classification
Image classification is the process of teaching a computer to look at a picture and decide what category or label best describes the main object or scene in that picture.
Key term
Service
A service is a software component or system that performs a specific function and is available to be used by other programs or users over a network.
About these practice questions
Courseiva writes every AI-900 question from scratch — 985 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or 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.