目录
 前辅文
 Chapter 1 Introduction
  1.1 Why Faces with Multi-Characteristics
  1.2 Facial Authentication Using Permanent Special Features
  1.3 Facial Beauty Analysis Using Permanent Common Features
  1.4 Facial Diagnosis by Disease Changed Features
  1.5 Expression Recognition by Stimulus Changed Features
  1.6 Outline of This Book
  References
 PART I FACIAL AUTHENTICATION
  Chapter 2 Facial Authentication Overview
   2.1 Introduction
    2.1.1 History of Automated Facial Recognition Research
    2.1.2 Classification of Facial Recognition Scenarios
    2.1.3 Challenges in Automated Facial Recognition
   2.2 Permanent Unique Features for Facial Recognition
    2.2.1 Geometric Features
    2.2.2 Appearance Features
   2.3 Facial Recognition: Systems and Applications
    2.3.1 Major Modules in Automated Facial Recognition Systems
    2.3.2 Application Modes
   2.4 Chapters Overview
   2.5 Summary
   References
  Chapter 3 Evolutionary Discriminant Feature Based Facial Recognition
   3.1 Introduction
   3.2 Evolutionary Discriminant Feature Extraction
    3.2.1 Data Preprocessing: Centralization and Whitening
    3.2.2 Calculating the Constrained Search Space
    3.2.3 Searching: An Evolutionary Approach
    3.2.4 Bagging EDFE
   3.3 Facial Recognition Experiments
    3.3.1 Databases and Parameter Settings
    3.3.2 Investigation on Different Subspaces
    3.3.3 Investigation on Dimensionality of Feature Subspaces
    3.3.4 Performance Comparison
    3.3.5 Discussion
   3.4 Summary
   References
  Chapter 4 Facial Identification by Gabor Feature Based Robust Representation
   4.1 Introduction
   4.2 Related Work
    4.2.1 Sparse Representation Based Classification (SRC)
    4.2.2 Collaborative Representation Based Classification (CRC)
    4.2.3 Gabor Features
   4.3 Gabor-Feature Based Robust Representation and Classification
    4.3.1 Gabor-Feature Based Robust Representation
    4.3.2 Discussion on Occlusion Dictionary
    4.3.3 Gabor Occlusion Dictionary (GOD) Computing
    4.3.4 GRR Based Classification (GRRC)
    4.3.5 Time Complexity
   4.4 Experimental Results
    4.4.1 Gabor Features and Regularization of GOD Computing
    4.4.2 Face Recognition with Little Deformation
    4.4.3 Face Recognition with Pose and Expression Variations
    4.4.4 Recognition Against Occlusion
   4.5 Discussion of Regularization on Coding Coefficients
   4.6 Summary
   References
  Chapter 5 Three Dimension Enhanced Facial Identification
   5.1 Introduction
   5.2 Joint Face Alignment and 3D Face Reconstruction
    5.2.1 Overview
    5.2.2 Training Data Preparation
    5.2.3 Learning Landmark Regressors
    5.2.4 Estimating 3D-to-2D Mapping and Landmark Visibility
   5.3 Application to Face Recognition
   5.4 Experiments
    5.4.1 Protocols
    5.4.2 3D Face Reconstruction Accuracy
    5.4.3 Face Alignment Accuracy
    5.4.4 Face Recognition Accuracy
    5.4.5 Computational Efficiency
   5.5 Summary
   References
 PART II FACIAL BEAUTY ANALYSIS
  Chapter 6 Facial Beauty Analysis Overview
   6.1 Introduction
   6.2 Permanent Common Features for Beauty Analysis
    6.2.1 Golden Ratio Rules
    6.2.2 Three Court Five
    6.2.3 Averageness Hypothesis
    6.2.4 Facial Symmetry and Beauty Perception
   6.3 Facial Beauty Analysis: Features and Systems
    6.3.1 Facial Feature Extraction
    6.3.2 Modeling Methods
    6.3.3 Applications
   6.4 Chapters Overview
   6.5 Summary
   References
  Chapter 7 Facial Beauty Analysis by Geometric Features
   7.1 Introduction
   7.2 Related Work
    7.2.1 Facial Geometric Representation
    7.2.2 Supervised Facial Beauty Model
    7.2.3 Facial Attractiveness Assessment
   7.3 Proposed Geometric Beauty Analysis Framework
    7.3.1 Geometric Beauty Analysis
    7.3.2 Hessian Regularization
    7.3.3 Hessian Semi-Supervised Learning with Random Projection
    7.3.4 Computational Complexity
    7.3.5 Remarks on the Convergence
   7.4 Experiments on the Proposed Dataset
    7.4.1 Our Established Dataset
    7.4.2 Low-Dimensional Distribution Visualization
    7.4.3 Experimental Results
    7.4.4 Verification
    7.4.5 Insightful Implications
   7.5 Experiment on M2B Dataset
    7.5.1 M2B Dataset
    7.5.2 Beauty Score Prediction
   7.6 Discussion
   7.7 Summary
   References
  Chapter 8 Facial Beauty Analysis by Landmark Model
   8.1 Introduction
   8.2 Related Work
   8.3 Key Point (KP) Definition
   8.4 Inserted Point (IP) Generation
    8.4.1 Quantitative Measure of the Precision of LMs
    8.4.2 Iterative Search for Optimal Positions of IPs
   8.5 The Optimized Landmark Model
    8.5.1 Training Data Preparation
    8.5.2 Generation and the Optimized LM
   8.6 Comparison with Other LMs
    8.6.1 Comparison of Approximation Error
    8.6.2 Comparison of Landmark Detection Error
   8.7 Applications
    8.7.1 Facial Beauty Analysis
    8.7.2 Facial Animation
   8.8 Summary
   References
  Chapter 9 A New Hypothesis for Facial Beauty Analysis
   9.1 Introduction
   9.2 Notations and the New Hypothesis
   9.3 Empirical Proof of the WA Hypothesis
    9.3.1 Face Image Dataset
    9.3.2 Attractiveness Score Collection
    9.3.3 Attractiveness Score Regression
    9.3.4 Testing the Hypothesis
   9.4 Corollary of the Hypothesis and Convex Hull-Based Face Beautification
    9.4.1 Corollary of the WA Hypothesis
    9.4.2 Convex Hull-Based Face Beautification
    9.4.3 Results
    9.4.4 Comparison and Discussion
   9.5 Compatibility with Other Hypotheses
    9.5.1 Compatibility with the Averageness Hypothesis
    9.5.2 Compatibility with the Symmetry Hypothesis
    9.5.3 Compatibility with the Golden Ratio Hypothesis
   9.6 Summary
   References
  Chapter 10 Facial Beauty Analysis: Prediction, Retrieval and Manipulation
   10.1 Introduction
   10.2 Facial Image Preprocessing and Feature Extraction
    10.2.1 Face Detection and Landmark Extraction
    10.2.2 Face Registration and Cropping
    10.2.3 Feature Extraction
   10.3 Facial Beauty Modeling
    10.3.1 Problem Formulation
    10.3.2 Regression Methods
   10.4 Facial Beauty Prediction
   10.5 Beauty-Oriented Face Retrieval
    10.5.1 Retrieval for Face Recommendation
    10.5.2 Retrieval for Face Beautification
   10.6 Facial Beauty Manipulation
    10.6.1 Exemplar-Based Manipulation
    10.6.2 Model-Based Manipulation
   10.7 Experiments
    10.7.1 Data Set
    10.7.2 Evaluation of Features for Facial Beauty Prediction
    10.7.3 Benefit of Soft Biometric Traits
    10.7.4 Results of Feature Fusion and Selection
    10.7.5 Results of Beauty-Oriented Face Retrieval
    10.7.6 Results of Facial Beauty Manipulation
   10.8 Summary
   References
 PART III FACIAL DIAGNOSIS
  Chapter 11 Facial Diagnosis Overview
   11.1 Introduction
   11.2 Disease Changing Features for Facial Diagnosis
   11.3 Computerized Facial Diagnosis
   11.4 Chapters Overview
   11.5 Summary
   References
  Chapter 12 Non-Invasive Diabetes Mellitus Detection Using Facial Colors
   12.1 Introduction
   12.2 Facial Images and Dataset
    12.2.1 Facial Image Acquisition Device
    12.2.2 Facial Block Definition
    12.2.3 Facial Image Dataset
   12.3 Facial Block Color Feature Extraction
   12.4 Healthy Versus DM Classification with the SRC
   12.5 Experimental Results
   12.6 Discussion
   12.7 Summary
   References
  Chapter 13 Health Status Analysis by Facial Texture Features
   13.1 Introduction
   13.2 Facial Image Acquisition Device
   13.3 Facial Image Pre-Processing and the Dataset
   13.4 Facial Image Texture Features Extraction
   13.5 Classification
   13.6 Experiments
   13.7 Summary
   References
  Chapter 14 Computerized Facial Diagnosis Using Both Color and Texture Features
   14.1 Introduction
   14.2 Facial Image Dataset
    14.2.1 Facial Image Acquisition Device
    14.2.2 Facial Image Dataset
    14.2.3 Facial Block Definition
   14.3 Facial Feature Extraction
    14.3.1 Color Feature Using Space Distribution
    14.3.2 Texture Feature Extracted by Gabor Filter
   14.4 Healthy Classification Using Facial Gloss
   14.5 Facial Block-Based Disease Analysis
    14.5.1 Diagnosis Using Single Block
    14.5.2 Optimal Blocks Combination
   14.6 Summary
   References
 PART IV FACIAL EXPRESSION RECOGNITION
  Chapter 15 Expression Recognition Overview
   15.1 Introduction
    15.1.1 Description of Facial Expressions
    15.1.2 Modalities in Facial Expression Recognition
    15.1.3 History of Facial Expression Recognition Research
    15.1.4 Challenges in Facial Expression Recognition
   15.2 Stimulus Changed Features for Expression Recognition
    15.2.1 Geometric vs. Appearance Features
    15.2.2 Global vs. Local Features
    15.2.3 Static vs. Dynamic Features
    15.2.4 Hand-crafted vs. Learned Features
   15.3 Facial Expression Recognition: Systems and Applications
    15.3.1 Workflow in Facial Expression Recognition Systems
    15.3.2 Applications
   15.4 Chapters Overview
   15.5 Summary
   References
  Chapter 16 Expression Recognition by Supervised LLE
   16.1 Introduction
   16.2 Independent Component Analysis
   16.3 Supervised Locally Linear Embedding
   16.4 Experiments
    16.4.1 Testing Methodology
    16.4.2 Experimental Results
   16.5 Summary
   References
  Chapter 17 Expression Recognition on Multiple Manifolds
   17.1 Introduction
   17.2 Multi-Manifold Based Facial Expression Recognition
    17.2.1 Learning Expression Manifolds
    17.2.2 Multi-Manifold Based Classification
    17.2.3 Dimensionality Selection
    17.2.4 The Procedures
   17.3 Experiments and Discussion
    17.3.1 Data Sets
    17.3.2 Feature Extraction
    17.3.3 Experimental Results
    17.3.4 Discussion
   17.4 Summary
   References
  Chapter 18 Cross Domain Facial Expression Recognition
   18.1 Introduction
   18.2 A Transfer Learning Based Approach
    18.2.1 Problem Formulation
    18.2.2 Overview of the Approach
    18.2.3 Training with Transfer Learning
    18.2.4 Evaluation Experiments
   18.3 A Discriminative Feature Adaptation Approach
    18.3.1 Problem Formulation
    18.3.2 Domain Matching
    18.3.3 Discriminative Analysis
    18.3.4 Optimization for DFA
    18.3.5 Evaluation Experiments
    18.3.6 Results and Discussion
   18.4 Summary
   References
  Chapter 19 Book Review and Future Work
   19.1 Book Recapitulation
   19.2 Challenges and Future Work
  Index
  插图
 前辅文
 Chapter 1 Introduction
  1.1 Why Faces with Multi-Characteristics
  1.2 Facial Authentication Using Permanent Special Features
  1.3 Facial Beauty Analysis Using Permanent Common Features
  1.4 Facial Diagnosis by Disease Changed Features
  1.5 Expression Recognition by Stimulus Changed Features
  1.6 Outline of This Book
  References
 PART I FACIAL AUTHENTICATION
  Chapter 2 Facial Authentication Overview
   2.1 Introduction
    2.1.1 History of Automated Facial Recognition Research
    2.1.2 Classification of Facial Recognition Scenarios
    2.1.3 Challenges in Automated Facial Recognition
   2.2 Permanent Unique Features for Facial Recognition
    2.2.1 Geometric Features
    2.2.2 Appearance Features
   2.3 Facial Recognition: Systems and Applications
    2.3.1 Major Modules in Automated Facial Recognition Systems
    2.3.2 Application Modes
   2.4 Chapters Overview
   2.5 Summary
   References
  Chapter 3 Evolutionary Discriminant Feature Based Facial Recognition
   3.1 Introduction
   3.2 Evolutionary Discriminant Feature Extraction
    3.2.1 Data Preprocessing: Centralization and Whitening
    3.2.2 Calculating the Constrained Search Space
    3.2.3 Searching: An Evolutionary Approach
    3.2.4 Bagging EDFE
   3.3 Facial Recognition Experiments
    3.3.1 Databases and Parameter Settings
    3.3.2 Investigation on Different Subspaces
    3.3.3 Investigation on Dimensionality of Feature Subspaces
    3.3.4 Performance Comparison
    3.3.5 Discussion
   3.4 Summary
   References
  Chapter 4 Facial Identification by Gabor Feature Based Robust Representation
   4.1 Introduction
   4.2 Related Work
    4.2.1 Sparse Representation Based Classification (SRC)
    4.2.2 Collaborative Representation Based Classification (CRC)
    4.2.3 Gabor Features
   4.3 Gabor-Feature Based Robust Representation and Classification
    4.3.1 Gabor-Feature Based Robust Representation
    4.3.2 Discussion on Occlusion Dictionary
    4.3.3 Gabor Occlusion Dictionary (GOD) Computing
    4.3.4 GRR Based Classification (GRRC)
    4.3.5 Time Complexity
   4.4 Experimental Results
    4.4.1 Gabor Features and Regularization of GOD Computing
    4.4.2 Face Recognition with Little Deformation
    4.4.3 Face Recognition with Pose and Expression Variations
    4.4.4 Recognition Against Occlusion
   4.5 Discussion of Regularization on Coding Coefficients
   4.6 Summary
   References
  Chapter 5 Three Dimension Enhanced Facial Identification
   5.1 Introduction
   5.2 Joint Face Alignment and 3D Face Reconstruction
    5.2.1 Overview
    5.2.2 Training Data Preparation
    5.2.3 Learning Landmark Regressors
    5.2.4 Estimating 3D-to-2D Mapping and Landmark Visibility
   5.3 Application to Face Recognition
   5.4 Experiments
    5.4.1 Protocols
    5.4.2 3D Face Reconstruction Accuracy
    5.4.3 Face Alignment Accuracy
    5.4.4 Face Recognition Accuracy
    5.4.5 Computational Efficiency
   5.5 Summary
   References
 PART II FACIAL BEAUTY ANALYSIS
  Chapter 6 Facial Beauty Analysis Overview
   6.1 Introduction
   6.2 Permanent Common Features for Beauty Analysis
    6.2.1 Golden Ratio Rules
    6.2.2 Three Court Five
    6.2.3 Averageness Hypothesis
    6.2.4 Facial Symmetry and Beauty Perception
   6.3 Facial Beauty Analysis: Features and Systems
    6.3.1 Facial Feature Extraction
    6.3.2 Modeling Methods
    6.3.3 Applications
   6.4 Chapters Overview
   6.5 Summary
   References
  Chapter 7 Facial Beauty Analysis by Geometric Features
   7.1 Introduction
   7.2 Related Work
    7.2.1 Facial Geometric Representation
    7.2.2 Supervised Facial Beauty Model
    7.2.3 Facial Attractiveness Assessment
   7.3 Proposed Geometric Beauty Analysis Framework
    7.3.1 Geometric Beauty Analysis
    7.3.2 Hessian Regularization
    7.3.3 Hessian Semi-Supervised Learning with Random Projection
    7.3.4 Computational Complexity
    7.3.5 Remarks on the Convergence
   7.4 Experiments on the Proposed Dataset
    7.4.1 Our Established Dataset
    7.4.2 Low-Dimensional Distribution Visualization
    7.4.3 Experimental Results
    7.4.4 Verification
    7.4.5 Insightful Implications
   7.5 Experiment on M2B Dataset
    7.5.1 M2B Dataset
    7.5.2 Beauty Score Prediction
   7.6 Discussion
   7.7 Summary
   References
  Chapter 8 Facial Beauty Analysis by Landmark Model
   8.1 Introduction
   8.2 Related Work
   8.3 Key Point (KP) Definition
   8.4 Inserted Point (IP) Generation
    8.4.1 Quantitative Measure of the Precision of LMs
    8.4.2 Iterative Search for Optimal Positions of IPs
   8.5 The Optimized Landmark Model
    8.5.1 Training Data Preparation
    8.5.2 Generation and the Optimized LM
   8.6 Comparison with Other LMs
    8.6.1 Comparison of Approximation Error
    8.6.2 Comparison of Landmark Detection Error
   8.7 Applications
    8.7.1 Facial Beauty Analysis
    8.7.2 Facial Animation
   8.8 Summary
   References
  Chapter 9 A New Hypothesis for Facial Beauty Analysis
   9.1 Introduction
   9.2 Notations and the New Hypothesis
   9.3 Empirical Proof of the WA Hypothesis
    9.3.1 Face Image Dataset
    9.3.2 Attractiveness Score Collection
    9.3.3 Attractiveness Score Regression
    9.3.4 Testing the Hypothesis
   9.4 Corollary of the Hypothesis and Convex Hull-Based Face Beautification
    9.4.1 Corollary of the WA Hypothesis
    9.4.2 Convex Hull-Based Face Beautification
    9.4.3 Results
    9.4.4 Comparison and Discussion
   9.5 Compatibility with Other Hypotheses
    9.5.1 Compatibility with the Averageness Hypothesis
    9.5.2 Compatibility with the Symmetry Hypothesis
    9.5.3 Compatibility with the Golden Ratio Hypothesis
   9.6 Summary
   References
  Chapter 10 Facial Beauty Analysis: Prediction, Retrieval and Manipulation
   10.1 Introduction
   10.2 Facial Image Preprocessing and Feature Extraction
    10.2.1 Face Detection and Landmark Extraction
    10.2.2 Face Registration and Cropping
    10.2.3 Feature Extraction
   10.3 Facial Beauty Modeling
    10.3.1 Problem Formulation
    10.3.2 Regression Methods
   10.4 Facial Beauty Prediction
   10.5 Beauty-Oriented Face Retrieval
    10.5.1 Retrieval for Face Recommendation
    10.5.2 Retrieval for Face Beautification
   10.6 Facial Beauty Manipulation
    10.6.1 Exemplar-Based Manipulation
    10.6.2 Model-Based Manipulation
   10.7 Experiments
    10.7.1 Data Set
    10.7.2 Evaluation of Features for Facial Beauty Prediction
    10.7.3 Benefit of Soft Biometric Traits
    10.7.4 Results of Feature Fusion and Selection
    10.7.5 Results of Beauty-Oriented Face Retrieval
    10.7.6 Results of Facial Beauty Manipulation
   10.8 Summary
   References
 PART III FACIAL DIAGNOSIS
  Chapter 11 Facial Diagnosis Overview
   11.1 Introduction
   11.2 Disease Changing Features for Facial Diagnosis
   11.3 Computerized Facial Diagnosis
   11.4 Chapters Overview
   11.5 Summary
   References
  Chapter 12 Non-Invasive Diabetes Mellitus Detection Using Facial Colors
   12.1 Introduction
   12.2 Facial Images and Dataset
    12.2.1 Facial Image Acquisition Device
    12.2.2 Facial Block Definition
    12.2.3 Facial Image Dataset
   12.3 Facial Block Color Feature Extraction
   12.4 Healthy Versus DM Classification with the SRC
   12.5 Experimental Results
   12.6 Discussion
   12.7 Summary
   References
  Chapter 13 Health Status Analysis by Facial Texture Features
   13.1 Introduction
   13.2 Facial Image Acquisition Device
   13.3 Facial Image Pre-Processing and the Dataset
   13.4 Facial Image Texture Features Extraction
   13.5 Classification
   13.6 Experiments
   13.7 Summary
   References
  Chapter 14 Computerized Facial Diagnosis Using Both Color and Texture Features
   14.1 Introduction
   14.2 Facial Image Dataset
    14.2.1 Facial Image Acquisition Device
    14.2.2 Facial Image Dataset
    14.2.3 Facial Block Definition
   14.3 Facial Feature Extraction
    14.3.1 Color Feature Using Space Distribution
    14.3.2 Texture Feature Extracted by Gabor Filter
   14.4 Healthy Classification Using Facial Gloss
   14.5 Facial Block-Based Disease Analysis
    14.5.1 Diagnosis Using Single Block
    14.5.2 Optimal Blocks Combination
   14.6 Summary
   References
 PART IV FACIAL EXPRESSION RECOGNITION
  Chapter 15 Expression Recognition Overview
   15.1 Introduction
    15.1.1 Description of Facial Expressions
    15.1.2 Modalities in Facial Expression Recognition
    15.1.3 History of Facial Expression Recognition Research
    15.1.4 Challenges in Facial Expression Recognition
   15.2 Stimulus Changed Features for Expression Recognition
    15.2.1 Geometric vs. Appearance Features
    15.2.2 Global vs. Local Features
    15.2.3 Static vs. Dynamic Features
    15.2.4 Hand-crafted vs. Learned Features
   15.3 Facial Expression Recognition: Systems and Applications
    15.3.1 Workflow in Facial Expression Recognition Systems
    15.3.2 Applications
   15.4 Chapters Overview
   15.5 Summary
   References
  Chapter 16 Expression Recognition by Supervised LLE
   16.1 Introduction
   16.2 Independent Component Analysis
   16.3 Supervised Locally Linear Embedding
   16.4 Experiments
    16.4.1 Testing Methodology
    16.4.2 Experimental Results
   16.5 Summary
   References
  Chapter 17 Expression Recognition on Multiple Manifolds
   17.1 Introduction
   17.2 Multi-Manifold Based Facial Expression Recognition
    17.2.1 Learning Expression Manifolds
    17.2.2 Multi-Manifold Based Classification
    17.2.3 Dimensionality Selection
    17.2.4 The Procedures
   17.3 Experiments and Discussion
    17.3.1 Data Sets
    17.3.2 Feature Extraction
    17.3.3 Experimental Results
    17.3.4 Discussion
   17.4 Summary
   References
  Chapter 18 Cross Domain Facial Expression Recognition
   18.1 Introduction
   18.2 A Transfer Learning Based Approach
    18.2.1 Problem Formulation
    18.2.2 Overview of the Approach
    18.2.3 Training with Transfer Learning
    18.2.4 Evaluation Experiments
   18.3 A Discriminative Feature Adaptation Approach
    18.3.1 Problem Formulation
    18.3.2 Domain Matching
    18.3.3 Discriminative Analysis
    18.3.4 Optimization for DFA
    18.3.5 Evaluation Experiments
    18.3.6 Results and Discussion
   18.4 Summary
   References
  Chapter 19 Book Review and Future Work
   19.1 Book Recapitulation
   19.2 Challenges and Future Work
  Index
  插图