Next Article in Journal
Theoretical and Experimental Study on Nonlinear Failure of an MEMS Accelerometer under Dual Frequency Acoustic Interference
Next Article in Special Issue
Surface Reconstruction from Structured Light Images Using Differentiable Rendering
Previous Article in Journal
Real-Time Production of PGA, PGV, Intensity, and Sa Shakemaps Using Dense MEMS-Based Sensors in Taiwan
Previous Article in Special Issue
Self-Supervised Point Set Local Descriptors for Point Cloud Registration
 
 
Article

A Systematic Comparison of Depth Map Representations for Face Recognition

1
DIEF—Dipartimento di Ingegneria Enzo Ferrari, Università Degli Studi di Modena e Reggio Emilia, 41125 Modena, Italy
2
DISI—Dipartimento di Informatica-Scienza e Ingegneria, Università di Bologna, 47521 Cesena, Italy
3
AIRI—Artificial Intelligence Research and Innovation Center, Università Degli Studi di Modena e Reggio Emilia, 41125 Modena, Italy
*
Author to whom correspondence should be addressed.
These authors contributed equally to this work.
Academic Editor: Sylvie Le Hegarat-Mascle
Sensors 2021, 21(3), 944; https://doi.org/10.3390/s21030944
Received: 23 December 2020 / Revised: 22 January 2021 / Accepted: 26 January 2021 / Published: 31 January 2021
(This article belongs to the Special Issue Computer Vision for 3D Perception and Applications)
Nowadays, we are witnessing the wide diffusion of active depth sensors. However, the generalization capabilities and performance of the deep face recognition approaches that are based on depth data are hindered by the different sensor technologies and the currently available depth-based datasets, which are limited in size and acquired through the same device. In this paper, we present an analysis on the use of depth maps, as obtained by active depth sensors and deep neural architectures for the face recognition task. We compare different depth data representations (depth and normal images, voxels, point clouds), deep models (two-dimensional and three-dimensional Convolutional Neural Networks, PointNet-based networks), and pre-processing and normalization techniques in order to determine the configuration that maximizes the recognition accuracy and is capable of generalizing better on unseen data and novel acquisition settings. Extensive intra- and cross-dataset experiments, which were performed on four public databases, suggest that representations and methods that are based on normal images and point clouds perform and generalize better than other 2D and 3D alternatives. Moreover, we propose a novel challenging dataset, namely MultiSFace, in order to specifically analyze the influence of the depth map quality and the acquisition distance on the face recognition accuracy. View Full-Text
Keywords: face recognition; depth maps; depth sensors; depth map representations; surface normal; point cloud; voxel; dataset face recognition; depth maps; depth sensors; depth map representations; surface normal; point cloud; voxel; dataset
Show Figures

Figure 1

MDPI and ACS Style

Pini, S.; Borghi, G.; Vezzani, R.; Maltoni, D.; Cucchiara, R. A Systematic Comparison of Depth Map Representations for Face Recognition. Sensors 2021, 21, 944. https://doi.org/10.3390/s21030944

AMA Style

Pini S, Borghi G, Vezzani R, Maltoni D, Cucchiara R. A Systematic Comparison of Depth Map Representations for Face Recognition. Sensors. 2021; 21(3):944. https://doi.org/10.3390/s21030944

Chicago/Turabian Style

Pini, Stefano, Guido Borghi, Roberto Vezzani, Davide Maltoni, and Rita Cucchiara. 2021. "A Systematic Comparison of Depth Map Representations for Face Recognition" Sensors 21, no. 3: 944. https://doi.org/10.3390/s21030944

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop