问题
Is there any AWS api for detecting live human in a video ? For example a person can fake the human detection by just showing an image of another person. So is there a way to overcome this ? The recognition will first verify if there is a person in the video or not. If not AWS is there any other api or python libraries to do that?
回答1:
Depending on the expected attack vector(s), it is likely going to be your responsibility to craft a solution comprised of other identity verification building blocks. Amazon Rekognition offers functionality that can be used for these tasks.
Depending on the expected levels of nefariousness of your userbase, one single sample data point (image) may not be sufficient for being able to robustly determine whether the subject is a human or not (nonetheless a specific one). Without additional datapoints like depth sensors, thermal imaging, and more, it is hard to definitively determine if someone is attempting to obfuscate with a mimicked face.
One method for increasing the robustness of such a system is to craft a multi-factor authentication layer with custom semi-random "tests" for users, including other information tests that would not be spoofed by physical attack vectors. A further way to increase robustness of the optical system would be to record video while asking the person to assume a sequence of poses or tasks (cover mouth, hand over right eye, tongue out) that are easy for a real person to do but not an imitation like this.
Amazon Rekognition supports finding faces within an image, as well as matching a test face to faces in a collection, and can also be used to help estimate other meta-concepts like emotion (happy, sad, frown, smile, etc). Rekognition video in particular can be used to detect changes while the user is changing from one pose to the next in an attempt to auto-detect bad actors.
来源：https://stackoverflow.com/questions/60541185/aws-live-human-detection-from-video