Robust Face Recognition with Deeply Normalized Depth Images

TL;DR

This paper introduces a deep learning approach that normalizes depth images of faces to a frontal pose and neutral expression, improving face recognition accuracy across varied poses and expressions.

Contribution

The paper presents a novel two-network system for normalizing depth images and extracting robust features, enhancing face recognition performance with depth data.

Findings

Outperforms existing methods in recognizing faces with different poses and expressions

Effective normalization of depth images improves recognition accuracy

Deep neural networks successfully reconstruct and normalize 3D face data

Abstract

Depth information has been proven useful for face recognition. However, existing depth-image-based face recognition methods still suffer from noisy depth values and varying poses and expressions. In this paper, we propose a novel method for normalizing facial depth images to frontal pose and neutral expression and extracting robust features from the normalized depth images. The method is implemented via two deep convolutional neural networks (DCNN), normalization network ($Net_{N}$) and feature extraction network ($Net_{F}$). Given a facial depth image, $Net_{N}$ first converts it to an HHA image, from which the 3D face is reconstructed via a DCNN. $Net_{N}$ then generates a pose-and-expression normalized (PEN) depth image from the reconstructed 3D face. The PEN depth image is finally passed to $Net_{F}$, which extracts a robust feature representation via another DCNN for face recognition. Our preliminary evaluation results demonstrate the superiority of the proposed method in recognizing faces of arbitrary poses and expressions with depth images.