AI-900 Practice Question: Describe features of computer vision workloads on Azure
An e-commerce website wants to automatically remove the background from product photos uploaded by sellers so that items appear on a consistent plain background. Which Azure Computer Vision capability should they use?
⚠ Common exam trap
Watch out — candidates often confuse Object Detection (which identifies objects) with Background Removal (which segments the entire foreground), leading them to choose D because they think detecting the product is sufficient to remove the background.
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
✓
Background Removal
Background Removal is the correct capability because it is specifically designed to isolate the foreground subject from the background in an image, producing a transparent or solid-color background. This directly meets the requirement of automatically removing backgrounds from product photos to create a consistent plain background. Azure's Background Removal API uses deep learning models trained on millions of images to segment the primary object from its surroundings.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Optical Character Recognition (OCR)
Why it's wrong here
OCR (implemented by Azure AI Vision's Read API) detects and extracts printed or handwritten text from an image, returning digitized text and word bounding boxes. It is a recognition capability, not an image-editing capability, so it cannot segment the person or product from its background or remove any pixels from the photo.
When this WOULD be correct
An exam question like 'Which Azure Computer Vision capability should be used to extract printed text from scanned invoices?' would make OCR the correct answer, as it specializes in text recognition.
- ✓
Background Removal
Why this is correct
Background removal is the correct service because it performs pixel-level semantic segmentation, classifying every pixel as either foreground subject or background and then producing an image with the background removed (often with a transparency mask). Unlike object detection, it does not return bounding boxes or labels; it actually alters the photo by isolating the main product for e-commerce display, which directly meets the stated requirement.
- ✗
Image Captioning
Why it's wrong here
Image captioning generates a natural-language sentence that describes the overall scene or salient objects by using vision-language transformer models. It only produces descriptive metadata about what is visible in the picture; it performs no pixel-level operations, so it cannot remove, replace, or isolate the background from the foreground object.
When this WOULD be correct
An exam question asking: 'Which Azure Computer Vision capability can automatically generate a human-readable description of a product photo for accessibility purposes?' would make Image Captioning the correct answer.
- ✗
Object Detection
Why it's wrong here
Object detection localizes objects of interest by drawing rectangular bounding boxes and assigning class labels around them. Those boxes typically include background regions and indicate only the object's position and rough extent; therefore, they do not provide the fine-grained pixel mask required to actually separate and remove the background from a product image.
When this WOULD be correct
An exam question asking: 'Which Computer Vision capability should be used to count the number of products in a warehouse photo and draw bounding boxes around each product?' would make Object Detection 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.
✓Background RemovalCorrect answer▾
Why this is correct
Background removal is the correct service because it performs pixel-level semantic segmentation, classifying every pixel as either foreground subject or background and then producing an image with the background removed (often with a transparency mask). Unlike object detection, it does not return bounding boxes or labels; it actually alters the photo by isolating the main product for e-commerce display, which directly meets the stated requirement.
✗Optical Character Recognition (OCR)Wrong answer — click to see why▾
Why this is wrong here
OCR extracts text from images, not background removal. The question asks for removing backgrounds from product photos, which is a segmentation task, not text extraction.
★ When this WOULD be the correct answer
An exam question like 'Which Azure Computer Vision capability should be used to extract printed text from scanned invoices?' would make OCR the correct answer, as it specializes in text recognition.
Why candidates choose this
Candidates may confuse OCR with general image processing, thinking it can 'clean up' images by removing text or other elements, but OCR only reads text, not removes backgrounds.
✗Image CaptioningWrong answer — click to see why▾
Why this is wrong here
Image Captioning generates descriptive text for an image, not background removal. The question specifically requires removing the background from product photos, which is a segmentation task, not a captioning task.
★ When this WOULD be the correct answer
An exam question asking: 'Which Azure Computer Vision capability can automatically generate a human-readable description of a product photo for accessibility purposes?' would make Image Captioning the correct answer.
Why candidates choose this
Candidates may confuse 'Image Captioning' with general image processing capabilities, assuming it can modify images, or they may think captioning involves editing the image itself rather than describing it.
✗Object DetectionWrong answer — click to see why▾
Why this is wrong here
Object Detection identifies and locates objects in an image, but does not remove backgrounds. The question specifically requires background removal, which is a distinct capability.
★ When this WOULD be the correct answer
An exam question asking: 'Which Computer Vision capability should be used to count the number of products in a warehouse photo and draw bounding boxes around each product?' would make Object Detection correct.
Why candidates choose this
Candidates may think object detection can isolate products from the background, confusing detection (locating objects) with segmentation (separating objects from background).
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
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
Deep learning
Deep learning is a subset of machine learning that uses multi-layered neural networks to automatically learn patterns from large amounts of data.
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 →
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.