Open abdou31 opened 5 years ago
If you have access to the entire face image you can use OpenFace directly to detect iris landmarks. However, if you only have the close up images of eyes, you would need a reasonable amount of work to adapt the eye region landmark detectors from OpenFace to detect iris landmarks. It is possible, but requires some work.
So , My question here , OpenFace using training to get resultats ? what algorithm used for training ? ( Yolo , R-CNN ,Fast R-CNN...)?
OpenFace uses a number of algorithms for inference of landmarks and expressions. The best description is in the following paper: https://ieeexplore.ieee.org/document/8373812
this documents is not free
You can also find the paper here - https://www.dropbox.com/s/ki1inrjcjbwm24j/FG2018_camera_ready.pdf?dl=0
Thanks
Hello , I have try to training my data using yolov3 darkne (library of AlexayAB ) to detect iris in real time (with webcam of smartphone for exemple ) , e.g: https://i.imgur.com/tZemyqp.png
I want to mixed yolo algorithm with Landmark detection ( or Keypoints detection ) to draw points takes the form of the iris after training and detection the iris region with yolo . I ask is it possible to do that? How to do that with openface?
Thanks,