What is the transformation matrix for Face Detection Landmarks anyways? #5803
Assignees
Labels
task:face detection
Issues related to Face Detection: Identify faces in images and video
type:support
General questions
Comments
kuaashish
added
task:face detection
|
Hi @ArdaSenyurek, In the context of MediaPipe's face detection, a transformation matrix is a mathematical tool that maps points from a 3D canonical face model to the corresponding detected face landmarks in a 2D image or 3D space. For further clarification, please refer to the following article. Thank you!! |
|
Can you please provide an example on how to use it? For example, given a 3D object, e.g glasses, we want to mount it on the face. What is the use of transformation matrix in this case? |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Description of issue (what needs changing)
Transformation Matrix for Face Detection
Clear description
What is the transformation matrix? What does it map from to what?
Correct links
No response
Parameters defined
No response
Returns defined
No response
Raises listed and defined
No response
Usage example
No response
Request visuals, if applicable
No response
Submit a pull request?
No response
The text was updated successfully, but these errors were encountered: