Title:
Face Processing and Applications to Distance Learning
Personal Author:
Physical Description:
xi, 126 pages : illustrations ; 24 cm.
ISBN:
9789814733021
Available:*
Library | Item Barcode | Call Number | Material Type | Item Category 1 | Status |
---|---|---|---|---|---|
Searching... | 33000000002347 | TA1650 L45 2016 | Open Access Book | Book | Searching... |
On Order
Summary
Summary
This special compendium provides a concise and unified vision of facial image processing. It addresses a collection of state-of-the-art techniques, covering the most important areas for facial biometrics and behavior analysis. These techniques also converge to serve an emerging practical application of interactive distance learning.Readers will get a broad picture of the fundamental science of the field and technical details that make the research interesting. Moreover, the intellectual investigation motivated by the demand of real-life application will make this volume an inspiring read for current and prospective researchers and engineers in the fields of computer vision, machine learning and image processing.
Table of Contents
Preface | p. vii |
1 Introduction | p. 1 |
1.1 Motivation | p. 2 |
1.2 Overview | p. 2 |
2 Facial Expression Recognition | p. 5 |
2.1 Introduction | p. 5 |
2.2 Related Work | p. 6 |
2.3 Image Features | p. 10 |
2.3.1 Mid-Level Features | p. 10 |
2.4 Supervised Image Descriptor Encoding | p. 14 |
2.4.1 Supervised Soft Vector Quantization (SSVQ) | p. 14 |
2.4.2 Multi-class SSVQ | p. 16 |
2.4.3 Supervised Super-Vector Encoding (SSE) | p. 17 |
2.5 Databases | p. 19 |
2.5.1 Binghamton University 3D Facial Expression (BU-3DFE) Database | p. 19 |
2.5.2 CMU Multi-PIE | p. 19 |
2.6 Experiments and Discussion | p. 20 |
2.7 Concluding Remarks | p. 27 |
3 3D Face Modeling | p. 29 |
3.1 Introduction | p. 29 |
3.2 3D Face Model Reconstruction from 2D Images | p. 31 |
3.2.1 Related Work | p. 32 |
3.2.2 3D Reconstruction from a Single Image of Arbitrary View | p. 32 |
3.2.3 3D Reconstruction from Stereo Images | p. 34 |
3.2.4 Experiments and Evaluation | p. 36 |
3.3 3D Face Model Tracking from 2D Videos | p. 42 |
3.3.1 Introduction | p. 42 |
3.3.2 Literature Review | p. 43 |
3.3.3 Real Time 3D Face 'Tracking from 2D Videos | p. 44 |
3.3.4 Experimental Results | p. 46 |
3.4 3D Face Modeling from RGB-D Images | p. 48 |
3.4.1 Introduction | p. 48 |
3.4.2 3D Face Model Fitting with RGB-D Signal | p. 49 |
3.4.3 3D Face Model Tracking with RGB-D Signal | p. 50 |
3.5 Conclusions | p. 52 |
4 Eye Gaze Estimation | p. 55 |
4.1 Introduction | p. 55 |
4.2 Previous Work | p. 56 |
4.2.1 Feature-based Methods | p. 56 |
4.2.2 Appearance-based Methods | p. 57 |
4.2.3 Geometric Model-based Methods | p. 58 |
4.2.1 Visible Light Methods | p. 58 |
4.3 Eye Gaze Estimation Using 3D Models | p. 59 |
4.3.1 3D Face Model Tracking | p. 60 |
4.3.2 Gaze Direction Estimation | p. 61 |
4.4 Experiments | p. 63 |
4.5 Conclusions | p. 66 |
5 Expressive Audio-visual Avatar | p. 67 |
5.1 Introduction | p. 67 |
5.2 Related Work | p. 68 |
5.2.1 Expressive Speech Synthesis | p. 68 |
5.2.2 3D Face Modeling and Animation | p. 69 |
5.2.3 Co-articulation of Lip Motion and Facial Expressions | p. 71 |
5.3 System Framework and Methods | p. 71 |
5.3.1 System Framework | p. 71 |
5.3.2 3D Face Modeling | p. 72 |
5.3.3 3D face Animation | p. 73 |
5.3.4 Expressive Speech Synthesis | p. 77 |
5.4 Evaluations | p. 83 |
5.5 Conclusions and Future Work | p. 85 |
6 Model Based Video Encoding | p. 87 |
6.1 Introduction | p. 87 |
6.2 Animation Model Construction | p. 87 |
6.3 Performance-driven Animations | p. 88 |
6.4 3D Model-based Video Coding | p. 90 |
6.5 Experimental Results | p. 90 |
7 Student Engagement Monitoring | p. 93 |
7.1 Introduction | p. 93 |
7.2 Related Work | p. 94 |
7.3 System Overview | p. 95 |
7.4 Engagement Estimation | p. 96 |
7.4.1 Gaze Direction | p. 96 |
7.4.2 Emotion Recognition | p. 97 |
7.5 Experiments | p. 99 |
7.5.1 Qualitative Evaluation | p. 99 |
7.5.2 Quantitative Evaluation | p. 100 |
7.6 Conclusions and Future Work | p. 102 |
8 Conclusion and Future Work | p. 103 |
8.1 Robust Visual Tracking and Motion Model | p. 104 |
8.2 Client-cloud Architecture | p. 104 |
8.3 Residual Compensation for Photorealistic Video Coding | p. 105 |
Bibliography | p. 109 |
Index | p. 121 |