Deep Learning-based Single Image Face Depth Data Enhancement

TL;DR

This paper introduces a deep learning method using U-Net architectures to enhance face depth data from low-cost cameras, improving biometric security and presentation attack detection by reducing depth inaccuracies and holes.

Contribution

It presents a novel deep learning face depth enhancement approach that outperforms existing methods and maintains security by minimizing falsification of non-face depth data.

Findings

Deep learning enhancers outperform hand-crafted methods.

Enhanced depth data improves presentation attack detection.

Method maintains security by avoiding false depth falsification.

Abstract

Face recognition can benefit from the utilization of depth data captured using low-cost cameras, in particular for presentation attack detection purposes. Depth video output from these capture devices can however contain defects such as holes or general depth inaccuracies. This work proposes a deep learning face depth enhancement method in this context of facial biometrics, which adds a security aspect to the topic. U-Net-like architectures are utilized, and the networks are compared against hand-crafted enhancer types, as well as a similar depth enhancer network from related work trained for an adjacent application scenario. All tested enhancer types exclusively use depth data as input, which differs from methods that enhance depth based on additional input data such as visible light color images. Synthetic face depth ground truth images and degraded forms thereof are created with help of PRNet, to train multiple deep learning enhancer models with different network sizes and training configurations. Evaluations are carried out on the synthetic data, on Kinect v1 images from the KinectFaceDB, and on in-house RealSense D435 images. These evaluations include an assessment of the falsification for occluded face depth input, which is relevant to biometric security. The proposed deep learning enhancers yield noticeably better results than the tested preexisting enhancers, without overly falsifying depth data when non-face input is provided, and are shown to reduce the error of a simple landmark-based PAD method.