Exam AI-102 topic 2 question 23 discussion

B is the answer. https://learn.microsoft.com/en-us/azure/cognitive-services/computer-vision/how-to/use-headpose#detect-head-gestures You can detect head gestures like nodding and head shaking by tracking HeadPose changes in real time. You can use this feature as a custom liveness detector. Liveness detection is the task of determining that a subject is a real person and not an image or video representation. A head gesture detector could serve as one way to help verify liveness, especially as opposed to an image representation of a person.

Validating that subjects are real people can be done by detecting natural head movements. The HeadPose attribute provides the orientation of the head, and checking for natural changes in this attribute over time can help determine if the subject is a real person or a static image B is correct

Because the Liveness Detection attribute is not in the list, HeadPose is the right answer

I say this answer is B. Please hurry up and transport the meat.

FaceAttributes.HeadPose is used this solution.

"You need to use the Face service to validate that the subjects of the videos are real people." Never think too much into these questions. A can detect if it's real or not. Not asking anything else. It's A.

https://learn.microsoft.com/en-us/azure/cognitive-services/computer-vision/how-to/use-headpose#detect-head-gestures

It can’t be A. If you only try to detect the faces without tracking their position over time, the system can be easily fooled in this very specific scenario.

Option A is more appropriate for validating the presence of real people in the live video. By calling the face detection API and retrieving the face rectangle using the FaceRectangle attribute, you can detect and locate faces within the video frames. This helps in confirming the presence of actual human faces in the captured video. Option B, on the other hand, suggests repeatedly calling the face detection API and checking for changes to the FaceAttributes.HeadPose attribute. While head pose analysis can provide information about the orientation of detected faces, it may not be the most reliable approach for validating the authenticity of the subjects as real people. Checking for changes in head pose alone may not be sufficient to differentiate between real people and other forms of visual representations.

B: https://learn.microsoft.com/en-us/azure/cognitive-services/computer-vision/how-to/use-headpose#detect-head-gestures

B: https://learn.microsoft.com/en-us/azure/cognitive-services/computer-vision/how-to/use-headpose#detect-head-gestures

B https://learn.microsoft.com/en-us/azure/cognitive-services/computer-vision/how-to/use-headpose#detect-head-gestures "Liveness detection is the task of determining that a subject is a real person and not an image or video representation"

The Answer is B. A could be a still picture

The answer is B Detect head gestures You can detect head gestures like nodding and head shaking by tracking HeadPose changes in real time. You can use this feature as a custom liveness detector. Reference https://learn.microsoft.com/en-us/azure/cognitive-services/computer-vision/how-to/use-headpose