Three-Dimensional Face Recognition in the Presence of Facial Expressions: An Annotated Deformable Model Approach

In this paper, we present the computational tools and a hardware prototype for 3D face recognition. Full automation is provided through the use of advanced multistage alignment algorithms, resilience to facial expressions by employing a deformable model framework, and invariance to 3D capture device...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on pattern analysis and machine intelligence 2007-04, Vol.29 (4), p.640-649
Main Authors: Kakadiaris, I.A., Passalis, G., Toderici, G., Murtuza, M.N., Yunliang Lu, Karampatziakis, N., Theoharis, T.
Format: Article
Language:English
Subjects:
Algorithms
Artificial Intelligence
Automation
Biometry - methods
Computer science
Computer Simulation
Deformable models
Deformation
Devices
Face - anatomy & histology
Face and gesture recognition
Face recognition
Facial
Facial Expression
Formability
Hardware
Humans
Image Interpretation, Computer-Assisted - methods
Imaging, Three-Dimensional - methods
Information retrieval
information search and retrieval
Models, Biological
Pattern Recognition, Automated - methods
Prototypes
Reproducibility of Results
Resilience
Scalability
Sensitivity and Specificity
Three dimensional
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, we present the computational tools and a hardware prototype for 3D face recognition. Full automation is provided through the use of advanced multistage alignment algorithms, resilience to facial expressions by employing a deformable model framework, and invariance to 3D capture devices through suitable preprocessing steps. In addition, scalability in both time and space is achieved by converting 3D facial scans into compact metadata. We present our results on the largest known, and now publicly available, face recognition grand challenge 3D facial database consisting of several thousand scans. To the best of our knowledge, this is the highest performance reported on the FRGC v2 database for the 3D modality
ISSN:0162-8828
1939-3539
2160-9292
DOI:10.1109/TPAMI.2007.1017