A method of face recognition using 3D facial surfaces

Face recognition is one of the most rapidly developing areas of image processing and computer vision. In this work, a new method for face recognition and identification using 3D facial surfaces is proposed. The method is invariant to facial expression and pose variations in the scene. The method use...

Full description

Saved in:
Bibliographic Details
Published in:Journal of communications technology & electronics 2017-06, Vol.62 (6), p.648-652
Main Authors: Echeagaray-Patrón, B. A., Kober, V. I., Karnaukhov, V. N., Kuznetsov, V. V.
Format: Article
Language:English
Subjects:
3-D graphics
Biometry
Color
Communications Engineering
Comparative analysis
Computer vision
Conformal mapping
Engineering
Face
Face recognition
Facial recognition technology
Image processing
Invariants
Mathematical Models and Computational Methods
Methods
Networks
Object recognition
Pattern recognition systems
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:Face recognition is one of the most rapidly developing areas of image processing and computer vision. In this work, a new method for face recognition and identification using 3D facial surfaces is proposed. The method is invariant to facial expression and pose variations in the scene. The method uses 3D shape data without color or texture information. The method is based on conformal mapping of original facial surfaces onto a Riemannian manifold, followed by comparison of conformal and isometric invariants computed in this manifold. Computer results are presented using known 3D face databases that contain significant amount of expression and pose variations.
ISSN:1064-2269
1555-6557
DOI:10.1134/S1064226917060067