An SE(3) invariant description for 3D face recognition

Abstract Here, we intend to introduce a novel 3D face description which is invariant under the Special Euclidean group SE(3) and independent to the original surface parameterization. It is well known that it is too difficult to define a relative invariant parameterization of a general curved surface. In the present work, we introduce the multi-polar geodesic representation of ℝ3 surfaces. It allows to reach an isotropic canonical parameterization relatively to SE(3) due to the fact that the face surfaces can be easily assumed to be a graph of a function from ℝ2 to ℝ. The principal curvature fields according to a three-polar parameterization are considered. A statistical study is made to choose a good configuration of reference points. The performances of the novel description are tested on the standard database FRGC v2.0. Many recognition scenarios are established. The obtained results are very competitive with the state of the art.

• Publication year

  2019

• Venue

  Image and Vision Computing

• Publication date

  2019-09-01

• Fields of study

  Mathematics, Computer Science

• Identifiers
  DOI 10.1016/J.IMAVIS.2019.06.016
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• An Invariant Three-polar Representation for R3 Surfaces: Robustness and Accuracy for 3D Faces Description

  2021cited by this paper
• Utilizing Deep Learning and 3DLBP for 3D Face Recognition

  2017cited by this paper
• Deep 3D face identification

  2017cited by this paper
• Principal Curvature Measures Estimation and Application to 3D Face Recognition

  2017cited by this paper
• Deep, dense and accurate 3D face correspondence for generating population specific deformable models

  2017cited by this paper
• Learning from Millions of 3D Scans for Large-Scale 3D Face Recognition

  2017cited by this paper
• Discriminative transfer learning with sparsity regularization for single-sample face recognition

  2017cited by this paper
• Location-sensitive sparse representation of deep normal patterns for expression-robust 3D face recognition

  2017cited by this paper
• A Two-Phase Weighted Collaborative Representation for 3D partial face recognition with single sample

  2016cited by this paper
• FaceNet: A unified embedding for face recognition and clustering

  2015cited by this paper
• A Curvelet-based approach for textured 3D face recognition

  2015cited by this paper
• 3-D Facial Landmark Localization With Asymmetry Patterns and Shape Regression from Incomplete Local Features

  2015cited by this paper
• DeepFace: Closing the Gap to Human-Level Performance in Face Verification

  2014cited by this paper
• Deeply learned face representations are sparse, selective, and robust

  2014cited by this paper
• Towards 3D Face Recognition in the Real: A Registration-Free Approach Using Fine-Grained Matching of 3D Keypoint Descriptors

  2014cited by this paper
• Deep Learning Face Representation from Predicting 10,000 Classes

  2014cited by this paper
• A Stable and Invariant Three-polar Surface Representation: Application to 3D Face Description

  2014cited by this paper
• 3D FACE RECOGNITION FROM RANGE IMAGES BASED ON CURVATURE ANALYSIS

  2014cited by this paper
• Dense 3D Face Correspondence

  2014cited by this paper
• An efficient 3D face recognition approach based on the fusion of novel local low-level features

  2013cited by this paper
• A Machine-Learning Approach to Keypoint Detection and Landmarking on 3D Meshes

  2013cited by this paper
• Matching 3D face scans using interest points and local histogram descriptors

  2013cited by this paper
• 3D Facial Landmark Detection under Large Yaw and Expression Variations

  2013cited by this paper
• Iterative Closest Normal Point for 3D Face Recognition

  2013cited by this paper
• A robust invariant bipolar representation for R3 surfaces: applied to the face description

  2012cited by this paper
• A new 3D surface registration approach depending on a suited resolution: Application to 3D faces

  2012cited by this paper
• 3-D Face Recognition Using eLBP-Based Facial Description and Local Feature Hybrid Matching

  2012cited by this paper
• 3D Face Recognition Based on Curvature Feature Matching, with Expression Variation

  2012cited by this paper
• Face recognition using Eigenfaces

  2011cited by this paper
• Robust 3D Face Recognition by Local Shape Difference Boosting

  2010cited by this paper
• 3D Face Recognition Using Isogeodesic Stripes

  2010cited by this paper
• 3D Face recognition using distinctiveness enhanced facial representations and local feature hybrid matching

  2010cited by this paper
• Automatic 3D Face Recognition Using Fourier Descriptors

  2009cited by this paper
• Nonlinear Dimensionality Reduction for Face Recognition

  2009cited by this paper
• A coarse-to-fine curvature analysis-based rotation invariant 3D face landmarking

  2009cited by this paper
• A high-resolution 3D dynamic facial expression database

  2008cited by this paper
• A Region Ensemble for 3-D Face Recognition

  2008cited by this paper
• Keypoint Detection and Local Feature Matching for Textured 3D Face Recognition

  2007cited by this paper
• An Efficient Multimodal 2D-3D Hybrid Approach to Automatic Face Recognition

  2007cited by this paper
• Multiple Nose Region Matching for 3D Face Recognition under Varying Facial Expression

  2006cited by this paper
• Three-Dimensional Face Recognition Using Shapes of Facial Curves

  2006cited by this paper
• A 3D facial expression database for facial behavior research

  2006cited by this paper
• Overview of the face recognition grand challenge

  2005cited by this paper
• Performance of Geometrix ActiveID^TM 3D Face Recognition Engine on the FRGC Data

  2005cited by this paper
• The Augmented Multiresolution Reeb Graph Approach for Content-based Retrieval of 3d Shapes

  2005cited by this paper
• Evaluation of 3D Face Recognition in the presence of facial expressions: an Annotated Deformable Model approach

  2005cited by this paper
• Automatic 3D Face Recognition Using Topological Techniques

  2005cited by this paper
• Classifying range images of human faces with Hausdorff distance

  2000cited by this paper
• Towards a unitary formulation for invariant image description: application to image coding

  1998cited by this paper
• The expectation-maximization algorithm

  1996cited by this paper
• Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection

  1996cited by this paper
• Applications of Invariance in Computer Vision

  1993cited by this paper
• Geometric invariance in computer vision

  1992cited by this paper
• Stability of invariant Fourier descriptors and its inference in the shape classification

  1992cited by this paper
• A Method for Registration of 3-D Shapes

  1992cited by this paper
• Surface coding based on Morse theory

  1991cited by this paper
• A Complete Set of Fourier Descriptors for Two-Dimensional Shapes

  1982cited by this paper
• A comprehensive introduction to differential geometry

  1979cited by this paper
• Lectures on classical differential geometry

  1951cited by this paper
• Noname manuscript No. (will be inserted by the editor) Elastic Shape Models for Face Analysis Using Curvilinear Coordinates

  year unknowncited by this paper

• A novel integral and SE(3)-invariant description for 3D face recognition

  2025influential citation
• Rotation-Invariant Convolution With Point Sort and Curvature Radius for Point Cloud Classification and Segmentation

  2025cites this paper
• 3D Model Reconstruction from the Equivariant Resampled Three-polar Representation

  2024cites this paper
• A face recognition taxonomy and review framework towards dimensionality, modality and feature quality

  2023cites this paper
• 3D Face Recognition: Two Decades of Progress and Prospects

  2023cites this paper
• Face-GCN: A Graph Convolutional Network for 3D Dynamic Face Recognition

  2022cites this paper
• Face-GCN: A Graph Convolutional Network for 3D Dynamic Face Identification/Recognition

  2021cites this paper
• A geodesic multipolar parameterization-based representation for 3D face recognition

  2021cites this paper