Learning 3D Face-Animation Model

2005 ◽  
pp. 1807-1814
Author(s):  
Zhen Wen ◽  
Pengyu Hong ◽  
Jilin Tu ◽  
Thomas S. Huang
Keyword(s):  
Virtual Environments ◽  
Human Face ◽  
3D Face ◽  
Face Animation ◽  
Computer Aided ◽  
Synthetic Agents

A synthetic human face is useful for visualizing information related to the human face. The applications include visual telecommunication (Aizawa & Huang, 1995), virtual environments and synthetic agents (Pandzic, Ostermann, & Millen, 1999), and computer-aided education.

3D Face Recognition Based on Symbolic FDA Using SVM Classifier with Similarity and Dissimilarity Distance Measure

2017 ◽  
Vol 31 (04) ◽  
pp. 1756006 ◽  
Author(s):  
Manjunatha Hiremath ◽  
P. S. Hiremath
Keyword(s):  
Face Recognition ◽  
Distance Measure ◽  
Svm Classifier ◽  
Depth Information ◽  
3D Face Recognition ◽  
Emotional States ◽  
Range Images ◽  
Human Face ◽  
Biometric Technology ◽  
3D Face

Human face images are the basis not only for person recognition, but for also identifying other attributes like gender, age, ethnicity, and emotional states of a person. Therefore, face is an important biometric identifier in the law enforcement and human–computer interaction (HCI) systems. The 3D human face recognition is emerging as a significant biometric technology. Research interest into 3D face recognition has increased during recent years due to availability of improved 3D acquisition devices and processing algorithms. A 3D face image is represented by 3D meshes or range images which contain depth information. In this paper, the objective is to propose a new 3D face recognition method based on radon transform and symbolic factorial discriminant analysis using KNN and SVM classifier with similarity and dissimilarity measures, which are applied on 3D facial range images. The experimentation is done using three publicly available databases, namely, Bhosphorus, Texas and CASIA 3D face database. The experimental results demonstrate the effectiveness of the proposed method.

REPRESENTING 3D FACE FROM POINT CLOUD TO FACE-ALIGNED SPHERICAL DEPTH MAP

2012 ◽  
Vol 26 (01) ◽  
pp. 1255003 ◽  
Author(s):  
PEIJIANG LIU ◽  
YUNHONG WANG ◽  
ZHAOXIANG ZHANG
Keyword(s):  
Point Cloud ◽  
Special Kind ◽  
Depth Map ◽  
Face Verification ◽  
Face Alignment ◽  
Range Image ◽  
Human Face ◽  
3D Face ◽  
Face Shape ◽  
The Face

We propose a novel representation of 3D face shape which is a key step for feature extraction and face recognition. The input of the proposed methods is unstructured point cloud, which determines the wide applicability of the proposed representation. Our contributions mainly include two parts: Spherical Depth Map (SDM) and face alignment based on SDM. SDM, which can be adopted to many applications, is a special kind of range image utilizing the prior anatomical knowledge of human face. Useful characteristics of SDM facilitate face alignment with higher efficiency and accuracy. Experiments conducted on three popular 3D face databases verify the high efficacy and superiority of the proposed method. The accuracy of face alignment is up to 100% with our strategy. The face verification rates based on the standard protocols are all higher than the baseline performance of FRGC2.0.

A New Parameterised Feature-Based Generic 3D Human Face Model for Emotional Bio-Robots

2013 ◽  
Vol 461 ◽  
pp. 838-847
Author(s):  
Xu Zhang ◽  
Shu Jun Zhang ◽  
Kevin Hapeshi
Keyword(s):  
Facial Expressions ◽  
Computer Game ◽  
Human Face ◽  
Human Beings ◽  
Freeform Surfaces ◽  
Face Model ◽  
3D Face ◽  
Potential Applications ◽  
Feature Based ◽  
Human Faces

To represent various human facial expressions is an essential requirement for emotional bio-robots. The human expressions can convey certain emotions for communications of human beings with some muscles positions and their movements. To design and develop emotional robots, it is necessary to build a generic 3D human face model. While the geometrical features of human faces are freeform surfaces with complex properties, it is the fundamental requirement for the model to have the ability of representing both primitive and freeform surfaces. This requirement makes the Non-rational Uniform B-Spline (NURBS) are suitable for 3D human face modelling. In this paper, a new parameterised feature based generic 3D human face model is proposed and implemented. Based on observation of human face anatomy, the authors define thirty-four NURBS curve features and twenty-one NURBS surface features to represent the human facial components, such as eyebrows, eyes, nose and mouth etc. These curve models and surface models can be used to simulate different facial expressions by manipulating the control points of those NURBS features. Unlike the existing individual based face modelling methods, this parameterised 3D face model also gives users the ability to use the model imitate any face appearances. In addition the potential applications of the new proposed 3D face model are also discussed. Besides emotional bio-robots, it is believed that the proposed model can also be applied in other fields such as aesthetic plastic surgery simulation, film and computer game characters creation, and criminal investigation and prevention.

scholarly journals Fast Modelling Algorithm for Realistic Three-Dimensional Human Face for Film and Television Animation

Complexity ◽  
2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Limin Xu
Keyword(s):  
Three Dimensional ◽  
Reconstruction Method ◽  
Feature Points ◽  
Human Face ◽  
3D Face Reconstruction ◽  
3D Face ◽  
Film And Television ◽  
Face Reconstruction ◽  
Reconstruction Performance ◽  
The Face

Aiming at the face photos of film and television animation, this paper proposes a new fast three-dimensional (3D) face modelling algorithm. First of all, based on the LBF algorithm, this paper proposes a multifeature selection idea to automatically detect multiple features of the face. Secondly, in order to solve the shortcomings of slow training speed while achieving large pose face alignment, the regression-based CNN is selected as the algorithm to achieve fast convergence. Then, due to the influence of various factors, the extracted feature points are not completely correct, and Gabor features are used to screen the matching of feature points. Finally, by analysing the principle of 3DMM 3D face reconstruction, a single-view 3D face reconstruction method based on CNN is proposed. The experimental results show that the algorithm in this paper has good reconstruction performance and real-time performance and can realize the rapid modelling of human face.

Learning 3D Face Deformation Model

2011 ◽  
pp. 317-340
Author(s):  
Zhen Wen ◽  
Pengyu Hong ◽  
Jilin Tu ◽  
Thomas S. Huang
Keyword(s):  
Motion Analysis ◽  
Deformation Model ◽  
Interpolation Scheme ◽  
Unified Framework ◽  
3D Face ◽  
Facial Motion ◽  
Face Animation ◽  
Mesh Topology ◽  
Modeling Analysis ◽  
Analysis And Synthesis

This chapter presents a unified framework for machine-learning-based facial deformation modeling, analysis and synthesis. It enables flexible, robust face motion analysis and natural synthesis, based on a compact face motion model learned from motion capture data. This model, called Motion Units (Muss), captures the characteristics of real facial motion. The MU space can be used to constrain noisy low-level motion estimation for robust facial motion analysis. For synthesis, a face model can be deformed by adjusting the weights of Mus. The weights can also be used as visual features to learn audio-to-visual mapping using neural networks for real-time, speech-driven, 3D face animation. Moreover, the framework includes parts-based MUs because of the local facial motion and an interpolation scheme to adapt MUs to arbitrary face geometry and mesh topology. Experiments show we can achieve natural face animation and robust non-rigid face tracking in our framework.

Sign in / Sign up

Export Citation Format

Share Document