real-time face detection by Paul Viola and Michael Jones
2001
computer chips were very slow but still able to do face detection in near real-time
2006- after 5 years
Fujifilme rolled out the first digital camera that has a real-time face detector
ver
pre : read python and numpy tutorial
the problem: semantic gap (difference between computer and human)
challenges: viewpoint variation (camera moves)/ illumination/ deformation(poses and positions)/ occulsion/ background clutter( look similar with ba
a loss function tells how good our current classifier is
You tell your algorithm what kind of errors you care about and what kind of errors you trade off against
Multi-class SVM loss
–– j could be the number of classes our dataset have
-syi – the sco
