eduzhai > Applied Sciences > Engineering >

Face Authentication from Grayscale Coded Light Field

  • Save

... pages left unread,continue reading

Document pages: 5 pages

Abstract: Face verification is a fast-growing authentication tool for everyday systems,such as smartphones. While current 2D face recognition methods are veryaccurate, it has been suggested recently that one may wish to add a 3D sensorto such solutions to make them more reliable and robust to spoofing, e.g.,using a 2D print of a person s face. Yet, this requires an additionalrelatively expensive depth sensor. To mitigate this, we propose a novelauthentication system, based on slim grayscale coded light field imaging. Weprovide a reconstruction free fast anti-spoofing mechanism, working directly onthe coded image. It is followed by a multi-view, multi-modal face verificationnetwork that given grayscale data together with a low-res depth map achievescompetitive results to the RGB case. We demonstrate the effectiveness of oursolution on a simulated 3D (RGBD) version of LFW, which will be made public,and a set of real faces acquired by a light field computational camera.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×