# Which is best FaceNet or dlib_face_recognition_resnet_model_v1?

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 ?