Face Authentication from Grayscale Coded Light Field
This addresses the need for affordable and reliable anti-spoofing in face verification for everyday systems like smartphones, though it is incremental by building on existing 3D sensing ideas.
The authors tackled the problem of making face authentication more robust to spoofing without expensive depth sensors by proposing a system based on grayscale coded light field imaging, achieving competitive results to RGB-based methods on simulated and real datasets.
Face verification is a fast-growing authentication tool for everyday systems, such as smartphones. While current 2D face recognition methods are very accurate, it has been suggested recently that one may wish to add a 3D sensor to 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 additional relatively expensive depth sensor. To mitigate this, we propose a novel authentication system, based on slim grayscale coded light field imaging. We provide a reconstruction free fast anti-spoofing mechanism, working directly on the coded image. It is followed by a multi-view, multi-modal face verification network that given grayscale data together with a low-res depth map achieves competitive results to the RGB case. We demonstrate the effectiveness of our solution 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.