Imperial College London
Portrait Picture

ProfessorMichaelBronstein

Faculty of Engineering, Department of Computing

Visiting Professor
 
 
 
//

Contact

 

m.bronstein Website

 
 
//

Location

 

569Huxley BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Mahdi:2022:10.1109/tbiom.2021.3092564,
author = {Mahdi, SS and Nauwelaers, N and Joris, P and Bouritsas, G and Gong, S and Walsh, S and Shriver, MD and Bronstein, M and Claes, P},
doi = {10.1109/tbiom.2021.3092564},
journal = {IEEE Trans Biom Behav Identity Sci},
pages = {163--172},
title = {Matching 3D Facial Shape to Demographic Properties by Geometric Metric Learning: A Part-Based Approach.},
url = {http://dx.doi.org/10.1109/tbiom.2021.3092564},
volume = {4},
year = {2022}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - Face recognition is a widely accepted biometric identifier, as the face contains a lot of information about the identity of a person. The goal of this study is to match the 3D face of an individual to a set of demographic properties (sex, age, BMI, and genomic background) that are extracted from unidentified genetic material. We introduce a triplet loss metric learner that compresses facial shape into a lower dimensional embedding while preserving information about the property of interest. The metric learner is trained for multiple facial segments to allow a global-to-local part-based analysis of the face. To learn directly from 3D mesh data, spiral convolutions are used along with a novel mesh-sampling scheme, which retains uniformly sampled points at different resolutions. The capacity of the model for establishing identity from facial shape against a list of probe demographics is evaluated by enrolling the embeddings for all properties into a support vector machine classifier or regressor and then combining them using a naive Bayes score fuser. Results obtained by a 10-fold cross-validation for biometric verification and identification show that part-based learning significantly improves the systems performance for both encoding with our geometric metric learner or with principal component analysis.
AU  - Mahdi,SS
AU  - Nauwelaers,N
AU  - Joris,P
AU  - Bouritsas,G
AU  - Gong,S
AU  - Walsh,S
AU  - Shriver,MD
AU  - Bronstein,M
AU  - Claes,P
DO  - 10.1109/tbiom.2021.3092564
EP  - 172
PY  - 2022///
SP  - 163
TI  - Matching 3D Facial Shape to Demographic Properties by Geometric Metric Learning: A Part-Based Approach.
T2  - IEEE Trans Biom Behav Identity Sci
UR  - http://dx.doi.org/10.1109/tbiom.2021.3092564
UR  - https://www.ncbi.nlm.nih.gov/pubmed/36338273
VL  - 4
ER  -
Download