Few-data guided learning upon end-to-end point cloud network for 3D face recognition

Yu, Yi; Da, Feipeng; Zhang, Ziyu

doi:10.1007/s11042-022-12211-9

Cited by 8 publications

(5 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to enhance the robustness of the 3D point cloud face recognition system for multiple expressions and multiple poses, Gao et al [ 26 ] used point clouds as input and constructed a deep learning feature extraction network, ResPoint. Yu et al [ 27 ] modified PointNet and supplemented a few data-guided learning frameworks based on a Gaussian process morphable model for 3D face recognition. Cao et al [ 28 ] utilized PointNet++ and RoPS local descriptors to extract local features of a 3D face.…”

Section: Related Workmentioning

confidence: 99%

Point CNN:3D Face Recognition with Local Feature Descriptor and Feature Enhancement Mechanism

Wang,

Lei,

Qian

2023

Sensors

View full text Add to dashboard Cite

Three-dimensional face recognition is an important part of the field of computer vision. Point clouds are widely used in the field of 3D vision due to the simple mathematical expression. However, the disorder of the points makes it difficult for them to have ordered indexes in convolutional neural networks. In addition, the point clouds lack detailed textures, which makes the facial features easily affected by expression or head pose changes. To solve the above problems, this paper constructs a new face recognition network, which mainly consists of two parts. The first part is a novel operator based on a local feature descriptor to realize the fine-grained features extraction and the permutation invariance of point clouds. The second part is a feature enhancement mechanism to enhance the discrimination of facial features. In order to verify the performance of our method, we conducted experiments on three public datasets: CASIA-3D, Bosphorus, and Lock3Dface. The results show that the accuracy of our method is improved by 0.7%, 0.4%, and 0.8% compared with the latest methods on these three datasets, respectively.

show abstract

Section: Related Workmentioning

confidence: 99%

Point CNN:3D Face Recognition with Local Feature Descriptor and Feature Enhancement Mechanism

Wang,

Lei,

Qian

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Methods for extracting order-invariant features on point clouds were discussed for Pointnet [ 14 ] and Pointnet++ [ 15 ], which provide point-wise feature and hierarchical representations. The authors of [ 2 ] utilized this idea to solve point cloud face classification; however, this approach requires the learning of a Gaussian process morphable model [ 16 ] to encode the holistic features of real face samples to mitigate the intraclass variances from the face-scan phase.…”

Section: Related Workmentioning

confidence: 99%

“…As discussed in [ 2 , 26 ], research on the 3D facial recognition problem has developed in several major directions: (local) feature-based, (holistic) model-based, and matching-based methods. From a general perspective, we can see an underlying trend of reducing the necessity of the registration phase/domain matching—on account of the development of acquisition techniques that enforce more regular raw scanning results—while stronger computation methods and facilities progressively enable parallel processing on high-throughput data streams.…”

Section: Related Workmentioning

confidence: 99%

“…Later works, such as [ 1 , 3 ], concentrated on adapting a 2D learning framework for 3D scans, where a deep range image has commonly been utilized for medium representation, which might partially ignore the indifferentiability in spaces, e.g., 3D rotation by mass-supervised training. The authors of [ 2 ] provided an a priori model-based argumentation strategy to avoid the above-described question.…”

Section: Related Workmentioning

confidence: 99%

“…Solutions using the (semantic) model-matching process have achieved very high accuracy [ 1 ]; more recently, approaches using a 3D morphable model (3DMM) [ 2 ] have also achieved very high accuracy; however, the feasibility of key point detection and alignment relies on the constraints of large expression/pose variations.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Three-Dimensional Face Recognition Using Solid Harmonic Wavelet Scattering and Homotopy Dictionary Learning

Cheng

Yang

et al. 2022

Entropy

View full text Add to dashboard Cite

Data representation has been one of the core topics in 3D graphics and pattern recognition in high-dimensional data. Although the high-resolution geometrical information of a physical object can be well preserved in the form of metrical data, e.g., point clouds/triangular meshes, from a regular data (e.g., image/audio) processing perspective, they also bring excessive noise in the course of feature abstraction and regression. For 3D face recognition, preceding attempts focus on treating the scan samples as signals laying on an underlying discrete surface (mesh) or morphable (statistic) models and by embedding auxiliary information, e.g., texture onto the regularized local planar structure to obtain a superior expressive performance to registration-based methods, but environmental variations such as posture/illumination will dissatisfy the integrity or uniform sampling condition, which holistic models generally rely on. In this paper, a geometric deep learning framework for face recognition is proposed, which merely requires the consumption of raw spatial coordinates. The non-uniformity and non-grid geometric transformations in the course of point cloud face scanning are mitigated by modeling each identity as a stochastic process. Individual face scans are considered realizations, yielding underlying inherent distributions under the appropriate assumption of ergodicity. To accomplish 3D facial recognition, we propose a windowed solid harmonic scattering transform on point cloud face scans to extract the invariant coefficients so that unrelated variations can be encoded into certain components of the scattering domain. With these constructions, a sparse learning network as the semi-supervised classification backbone network can work on reducing intraclass variability. Our framework obtained superior performance to current competing methods; without excluding any fragmentary or severely deformed samples, the rank-1 recognition rate (RR1) achieved was 99.84% on the Face Recognition Grand Challenge (FRGC) v2.0 dataset and 99.90% on the Bosphorus dataset.

show abstract

Biometric Recognition Systems: A Short Survey

Sghaier,

Krichen,

Elfakki

et al. 2023

Lecture Notes in Networks and Systems

View full text Add to dashboard Cite

Few-data guided learning upon end-to-end point cloud network for 3D face recognition

Cited by 8 publications

References 51 publications

Point CNN:3D Face Recognition with Local Feature Descriptor and Feature Enhancement Mechanism

Point CNN:3D Face Recognition with Local Feature Descriptor and Feature Enhancement Mechanism

Three-Dimensional Face Recognition Using Solid Harmonic Wavelet Scattering and Homotopy Dictionary Learning

Biometric Recognition Systems: A Short Survey

Contact Info

Product

Resources

About