Three-dimensional (3D) facial recognition and prediction

Okuwobi, Idowu Paul; Chen, Qiang; Niu, Sijie; Bekalo, Loza

doi:10.1007/s11760-016-0871-z

Search citation statements

Order By: Relevance

Paper Sections

Select...

Gradient‐based Feature Extraction1

Introduction1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2017

2024

Publication Types

Select...

Article5

Book1

Relationship

Self Cite0

Independent6

Authors

Journals

Cited by 7 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Bagchi et al [34] extracted the significant depth values of the surface normals, then applying singular value decomposition stored them in the form of a feature vector. In [35], in order to improve the recognition accuracy, the normal surface vector and the principal curvature direction are used to obtain directional discrimination. Tang et al [36] described the LBP framework for the representation of 3D faces.…”

Section: Gradient‐based Feature Extractionmentioning

confidence: 99%

Use of gradient and normal vectors for face recognition

et al. 2020

View full text Add to dashboard Cite

Section: Gradient‐based Feature Extractionmentioning

confidence: 99%

Use of gradient and normal vectors for face recognition

et al. 2020

View full text Add to dashboard Cite

“…With this method, a set of spherical patches and curves are positioned over the nasal region to provide the feature descriptors. Okuwobi et al [14] used the principal curvature direction and the normal surface vector to obtain directional discrimination, in order to improve the recognition performance. The local feature-based methods are robust for image transformations such as illumination, rotation, and viewpoint changes, and their feature descriptors have low dimensions and are easy to match quickly.…”

Section: Introductionmentioning

confidence: 99%

Weighted Gradient Feature Extraction Based on Multiscale Sub-Blocks for 3D Facial Recognition in Bimodal Images

2018

View full text Add to dashboard Cite

In this paper, we propose a bimodal 3D facial recognition method aimed at increasing the recognition rate and reducing the effect of illumination, pose, expression, ages, and occlusion on facial recognition. There are two features extracted from the multiscale sub-blocks in both the 3D mode depth map and 2D mode intensity map, which are the local gradient pattern (LGP) feature and the weighted histogram of gradient orientation (WHGO) feature. LGP and WHGO features are cascaded to form the 3D facial feature vector LGP-WHGO, and are further trained and identified by the support vector machine (SVM). Experiments on the CASIA database, FRGC v2.0 database, and Bosphorus database show that, the proposed method can efficiently extract the structure information and texture information of the facial image, and have a robustness to illumination, expression, occlusion and pose.

show abstract