I am newbie in face recognition related things... As far i observed dlib's
frontal_face_detectoris widely used to find the faces in an image and after that, to extract face_descriptor vectors which is better for real time face authentication system ?
It looks both working fine.. but in real-time implementation,
Is there some thing important to understand the performance ?
Or any comparison checks done on real time / large data sets ?
Thanks in advance.