Exam AI-102 topic 1 question 37 discussion

A. Face. The solution link explains: Embed facial recognition into your apps for a seamless and highly secured user experience. No machine-learning expertise is required. Features include face detection that perceives facial features and attributes—such as a face mask, glasses, or face location—in an image, and identification of a person by a match to your private repository or via photo ID.

A is the answer. https://learn.microsoft.com/en-us/azure/cognitive-services/computer-vision/overview-identity#face-detection-and-analysis Face detection is required as a first step in all the other scenarios. The Detect API detects human faces in an image and returns the rectangle coordinates of their locations. It also returns a unique ID that represents the stored face data. This is used in later operations to identify or verify faces. Optionally, face detection can extract a set of face-related attributes, such as head pose, age, emotion, facial hair, and glasses. These attributes are general predictions, not actual classifications. Some attributes are useful to ensure that your application is getting high-quality face data when users add themselves to a Face service. For example, your application could advise users to take off their sunglasses if they're wearing sunglasses.

"A" makes sense. The task is to recognize people, that DO NOT wear their equipment, not to see who is wearing. Why check for social distancing, identifying masks, goggles, etc. if we only need to find the people that are not wearing that stuff and therefore are easily detected by Face.

Copilot: B To build a monitoring solution for staff compliance with PPE requirements, you should use B. Computer Vision. This service can analyze images and videos to detect whether staff are wearing masks or safety glasses. It is cost-effective and requires minimal development effort compared to other options

C is the right option

The best service to use is B. Computer Vision. Computer Vision can be used to detect and analyze objects in images, including PPE compliance like masks and safety glasses. It meets the requirements for identifying staff who have removed protective equipment, can be run at intervals (e.g., every 15 minutes), and minimizes both development effort and costs compared to more complex solutions like Azure Video Analyzer.

Face is not the best option to identify objects like masks so C Azure Video Analyzer for Media (formerly Video Indexer )

Facial recognition is lower effort than Video Indexer

It is C. Video Indexer https://learn.microsoft.com/en-us/azure/azure-video-indexer/video-indexer-overview#:~:text=Video%20models-,Face%20detection,-%3A%20Detects%20and%20groups

its this for sure

B is the answer according to Bing AI (ChatGPT). C is the answer according to Google gemini. I think C is the correct answer.

Answer is face

I think is Vision (using Spatial Analysis) https://techcommunity.microsoft.com/t5/ai-azure-ai-services-blog/cognitive-services-spatial-analysis-enables-safety-alerts-with/ba-p/3641130

Why is it not Computer Vision? I mean Computer Vision can analyse images or video frames to detect the presence or absence of specific objects for example masks. A scheduler can also be set up that captures images every 15 mins and then pass them to the Computer Vision service, and tbh it is also the most cost effective of all the options and has pre-built models

Even with an open book nobody can answer these kind of questions. The dysfunctional company like Microsoft seems to have outsourced this to another vendor and also charging them extra. Looks like they hired non-IT people to create these questions.

read this guys:https://learn.microsoft.com/en-us/azure/azure-video-indexer/video-indexer-overview Everybody is saying Face but this link shows exactly that it will not be sufficient. Its a shame A is voted best just because it mentions face. But face recognition will generate false positives. You will end up with a lot of people you cannot recognize due to mask. but any person that is not known as personel will also be not recognized, even though they dont wear a mask.

I tried to ask ChatGPT (also) reversing the question and there's no way: Computer Vision is always the solution to this problem