Describe features of computer vision workloads on Azure for Microsoft Azure AI Fundamentals (AI-900)

Sample Practice Questions

1. Question 1

   HOTSPOT - To complete the sentence, select the appropriate option in the answer area. Hot Area:
   Explanation

   Reference: https://docs.microsoft.com/en-us/azure/cognitive-services/computer-vision/concept-object-detection

2. Question 2

   You run a charity event that involves posting photos of people wearing sunglasses on Twitter. You need to ensure that you only retweet photos that meet the following requirements: Include one or more faces. Contain at least one person wearing sunglasses. What should you use to analyze the images?
   1. A. the Verify operation in the Face service
   2. B. the Detect operation in the Face service
   3. C. the Describe Image operation in the Computer Vision service
   4. D. the Analyze Image operation in the Computer Vision service
   Explanation

   The correct answer is: B. the Detect operation in the Face service.

   The requirement is to confirm two things in each photo: that at least one face appears, and that someone is wearing sunglasses. The Detect operation in Azure AI Face returns a bounding box for every face it finds and can also return facial landmarks and a set of attributes, with accessories such as glasses being one of the classic attributes reported, which covers both requirements in a single call. The Verify operation answers a different question, namely is this face the same person as that face, which is unrelated to counting faces or detecting sunglasses. The Describe Image operation in Azure AI Vision returns a free-text caption for the whole picture, which might mention sunglasses sometimes but is not a deterministic check. The Analyze Image operation in Azure AI Vision can return generic objects and tags, including a face indicator, but it does not report fine-grained facial accessories like glasses in the way Face Detect does, so Face Detect is the precise fit.

3. Question 3

   Which service should you use to extract text, key/value pairs, and table data automatically from scanned documents?
   1. A. Form Recognizer
   2. B. Text Analytics
   3. C. Language Understanding
   4. D. Custom Vision
   Explanation

   The correct answer is: A. Form Recognizer.

   Pulling text, key-value pairs, and table data from scanned documents is the headline workload of Azure AI Document Intelligence (formerly Form Recognizer), which ships with a layout model that returns raw text along with its table and key-value geometry, pre-built models for invoices, receipts, IDs, and business cards, and the ability to train custom models on your own forms. Text Analytics, now part of Azure AI Language, analyzes text that has already been extracted, performing sentiment analysis, key phrase extraction, named entity recognition, and language detection; it does not parse documents into structured fields. Language Understanding, now Conversational Language Understanding, classifies user utterances into intents and entities for chatbots, which is unrelated to forms. Custom Vision trains image classifiers and object detectors on labeled images and cannot read text or tables. Document Intelligence is the only choice that ingests the scanned document and returns all three of the requested artifacts.

4. Question 4

   HOTSPOT - To complete the sentence, select the appropriate option in the answer area. Hot Area:
   Explanation

   Accelerate your business processes by automating information extraction. Form Recognizer applies advanced machine learning to accurately extract text, key/ value pairs, and tables from documents. With just a few samples, Form Recognizer tailors its understanding to your documents, both on-premises and in the cloud. Turn forms into usable data at a fraction of the time and cost, so you can focus more time acting on the information rather than compiling it. Reference: https://azure.microsoft.com/en-us/services/cognitive-services/form-recognizer/

5. Question 5

   You are building a tool that will process images from retail stores and identify the products of competitors. The solution will use a custom model. Which Azure Cognitive Services service should you use?
   1. A. Custom Vision
   2. B. Form Recognizer
   3. C. Face
   4. D. Computer Vision
   Explanation

   The correct answer is: A. Custom Vision.

   The question hinges on the phrase a custom model, which signals you must train a model on your own labeled images rather than relying on a pre-built catalog. Azure AI Custom Vision is purpose-built for this: you upload images of the specific competitor products you want to recognize, tag them, and Custom Vision trains a classifier or object detector tailored to that exact set of items. Azure AI Document Intelligence (formerly Form Recognizer) extracts key-value pairs and tables from structured documents like invoices and receipts, which does not apply to identifying products on a shelf. Azure AI Face deals with detecting human faces and identifying named individuals, not retail products. Azure AI Vision (formerly Computer Vision) offers pre-built image analysis such as generic tags, captions, and well-known brand logos from a global database, but it cannot be trained on your specific competitor SKUs, so it does not satisfy the custom model requirement here.

Other Microsoft Azure AI Fundamentals (AI-900) domains

• Describe Artificial Intelligence workloads and considerations (76 questions)
• Describe features of Natural Language Processing (NLP) workloads on Azure (66 questions)
• Describe fundamental principles of machine learning on Azure (58 questions)