AI-900: Analyzing Images Ethically with Computer Vision AI

When using AI to process photos of people, responsible practices demand consent and care. Learn how tools like Microsoft’s Computer Vision service can help charities analyze images ethically.

Question

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?

A. the Verify operation in the Face service
B. the Detect operation in the Face service
C. the Describe Image operation in the Computer Vision service
D. the Analyze Image operation in the Computer Vision service

Answer

B. the Detect operation in the Face service

Explanation

The correct answer is B. You should use the Detect operation in the Face service to analyze the images.

The Detect operation in the Face service takes an image as input and returns an array of face objects, each containing information about the detected face, such as the face ID, face rectangle, face landmarks, and face attributes. One of the face attributes is glasses, which indicates the type of glasses the person is wearing. The possible values are NoGlasses, Sunglasses, ReadingGlasses, and SwimmingGoggles.

You can use the Detect operation to filter the images that meet your requirements by checking the following conditions:

• The length of the face array is greater than zero, which means that at least one face is detected in the image.
• At least one of the face objects in the array has the glasses attribute value equal to Sunglasses, which means that the person is wearing sunglasses.

The other options are not suitable for analyzing the images, because they do not provide the information you need.

The Verify operation in the Face service takes two face IDs as input and returns a confidence score indicating the similarity between the two faces. This operation is useful for identity verification or face recognition, but not for detecting faces or glasses in an image.

The Describe Image operation in the Computer Vision service takes an image as input and returns a description of the image in natural language, along with a confidence score and a list of tags. This operation is useful for generating captions or keywords for images, but not for detecting faces or glasses in an image.

The Analyze Image operation in the Computer Vision service takes an image as input and returns various features of the image, such as categories, tags, objects, faces, color, and adult content. This operation is useful for extracting general information from images, but not for detecting glasses in an image. The face feature only returns the face rectangle and the gender and age attributes, but not the glasses attribute.

Reference

Microsoft Learn > Azure > Cognitive Services > Computer Vision > What is the Azure Face service?

Microsoft Azure AI Fundamentals AI-900 certification exam practice question and answer (Q&A) dump with detail explanation and reference available free, helpful to pass the Microsoft Azure AI Fundamentals AI-900 exam and earn Microsoft Azure AI Fundamentals AI-900 certification.