Closed xieyipeng closed 1 year ago
The terminologies are largely used interchangeable. This reflects how historically face alignment/key points detection was performed: one would take a deformable facial model and align it with an image such that the model will now match the location of a set of desired fiducial points.
A good reference for this is the work from Gu&Kanade (https://link.springer.com/referenceworkentry/10.1007/978-0-387-73003-5_186)
This
face-alignment
is for face key point detection,But how should I do the real alignment operation?Like an affine transformation, keeping the eyes on the horizon?
I want to know the most formal, real alignment
thak u!