Muutke küpsiste eelistusi

Computer Models for Facial Beauty Analysis 1st ed. 2016 [Kõva köide]

5.00/5 (2 hinnangut Goodreads-ist)
, ,
  • Formaat: Hardback, 268 pages, kõrgus x laius: 235x155 mm, kaal: 5502 g, 141 Illustrations, black and white; XV, 268 p. 141 illus., 1 Hardback
  • Ilmumisaeg: 29-Apr-2016
  • Kirjastus: Springer International Publishing AG
  • ISBN-10: 3319325965
  • ISBN-13: 9783319325965
Teised raamatud teemal:
  • Kõva köide
  • Hind: 95,02 €*
  • * hind on lõplik, st. muud allahindlused enam ei rakendu
  • Tavahind: 111,79 €
  • Säästad 15%
  • Raamatu kohalejõudmiseks kirjastusest kulub orienteeruvalt 2-4 nädalat
  • Kogus:
  • Lisa ostukorvi
  • Tasuta tarne
  • Tellimisaeg 2-4 nädalat
  • Lisa soovinimekirja
Computer Models for Facial Beauty Analysis 1st ed. 2016Suurem pilt
  • Formaat: Hardback, 268 pages, kõrgus x laius: 235x155 mm, kaal: 5502 g, 141 Illustrations, black and white; XV, 268 p. 141 illus., 1 Hardback
  • Ilmumisaeg: 29-Apr-2016
  • Kirjastus: Springer International Publishing AG
  • ISBN-10: 3319325965
  • ISBN-13: 9783319325965
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9783319325965.html
Märksõnad:
This book covers the key advances in computerized facial beauty analysis, with an emphasis on data-driven research and the results of quantitative experiments. It takes a big step toward practical facial beauty analysis, proposes more reliable and stable facial features for beauty analysis and designs new models, methods, algorithms and schemes while implementing a facial beauty analysis and beautification system. This book also tests some previous putative rules and models for facial beauty analysis by using computationally efficient mathematical models and algorithms, especially large scale database-based and repeatable experiments. The first section of this book provides an overview of facial beauty analysis. The base of facial beauty analysis, i.e., facial beauty features, is presented in part two. Part three describes hypotheses on facial beauty, while part four defines data-driven facial beauty analysis models. This book concludes with the authors explaining how to implement

their new facial beauty analysis system. This book is designed for researchers, professionals and post graduate students working in the field of facial beauty analysis, computer vision, human-machine interface, pattern recognition and biometrics. Those involved in interdisciplinary fields with also find the contents useful. The ideas, means and conclusions for beauty analysis are valuable for researchers and the system design and implementation can be used as models for practitioners and engineers. 

Arvustused

  

Part I Introduction
1 Overview
3(16)
1.1 Background
3(2)
1.2 History of Facial Beauty Research
5(5)
1.2.1 Early Exploration of Facial Beauty
6(1)
1.2.2 Facial Beauty Study in Psychology
6(2)
1.2.3 Facial Beauty Study in Aesthetic Surgery
8(1)
1.2.4 Facial Beauty Study in Computer Science
9(1)
1.3 Key Problems and Difficulties
10(2)
1.3.1 Key Problems
10(1)
1.3.2 Difficulties
11(1)
1.4 Databases
12(2)
1.5 Arrangement of This Book
14(5)
1.5.1 PART I
14(1)
1.5.2 PART II
14(1)
1.5.3 PART III
14(1)
1.5.4 PART IV
15(1)
1.5.5 PART V
15(1)
References
16(3)
2 Typical Facial Beauty Analysis
19(16)
2.1 Introduction
19(1)
2.2 Golden Ratio Rules
20(1)
2.3 Vertical Thirds and Horizontal Fifths
21(1)
2.4 Averageness Hypothesis
22(2)
2.5 Facial Symmetry and Beauty Perception
24(1)
2.6 Facial Beauty Analysis by Biometrics Technology
25(4)
2.6.1 Databases Used in Existing Works
26(1)
2.6.2 Facial Feature Extraction
26(2)
2.6.3 Modeling Methods
28(1)
2.6.4 Applications
28(1)
2.7 Summary
29(6)
References
29(6)
Part II Facial Images and Features
3 Facial Landmark Model Design
35(18)
3.1 Introduction
35(4)
3.1.1 Landmark
35(1)
3.1.2 Landmark Model
36(3)
3.2 Key Point (KP) Definition
39(2)
3.3 Inserted Point (IP) Generation
41(3)
3.3.1 A Quantitative Measure of the Precision of LMs
42(1)
3.3.2 Iterative Search for Optimal Positions of IPs
43(1)
3.4 The Optimized Landmark Model
44(4)
3.4.1 Training Data Preparation
44(1)
3.4.2 IP Generation and the Optimized LM
45(3)
3.5 Comparison with Other Landmark Models
48(3)
3.5.1 Comparison of Approximation Error
48(2)
3.5.2 Comparison of Landmark Detection Error
50(1)
3.6 Summary
51(2)
References
51(2)
4 Geometrics Facial Beauty Study
53(16)
4.1 Introduction
53(1)
4.2 Preliminary Work
54(4)
4.2.1 Data Collection
54(1)
4.2.2 Feature Extraction
54(2)
4.2.3 Geometric Feature Normalization
56(2)
4.3 Landmark Model Evaluation Method
58(4)
4.3.1 Basic Statistical Analysis
58(1)
4.3.2 Principal Component Analysis (PCA)
59(1)
4.3.3 Multivariate Gaussian Model
60(1)
4.3.4 Model Evaluation
61(1)
4.4 Results and Discussions
62(4)
4.4.1 Mean Shape
62(1)
4.4.2 Main Modes of Variation
63(2)
4.4.3 Information Gain
65(1)
4.5 Summary
66(3)
References
67(2)
5 Putative Ratio Rules for Facial Beauty Indexing
69(20)
5.1 Introduction
69(2)
5.2 Data Preparation
71(4)
5.2.1 Average Face Dataset
71(1)
5.2.2 Landmark Extraction
71(2)
5.2.3 Collection of Putative Ratio Rules
73(2)
5.3 Multi-national Average Faces Clustering
75(2)
5.3.1 Measurement of Shape Differences
75(1)
5.3.2 k-Means Clustering
75(1)
5.3.3 Centers of Clusters
76(1)
5.4 Assessment and Correction of Putative Ratio Rules
77(4)
5.4.1 Criteria of Ratio Rule Assessment
78(1)
5.4.2 Experimental Results on the Whole Dataset and Individual Clusters
78(3)
5.5 Testing of the Corrected Ratio Rules
81(4)
5.5.1 Testing on Synthesized Faces
81(1)
5.5.2 Testing on Real Faces
82(3)
5.6 Summary
85(4)
Appendix 1
85(1)
Appendix 2
86(1)
References
87(2)
6 Beauty Analysis Fusion Model of Texture and Geometric Features
89(14)
6.1 Introduction
89(1)
6.2 Geometric and Texture Feature Extraction
90(5)
6.2.1 Geometric Feature Extraction
90(2)
6.2.2 Texture Feature Extraction
92(3)
6.3 Fusion Model Design
95(1)
6.4 Experiments and Analysis
96(3)
6.4.1 Experiments Using Geometric Features
97(1)
6.4.2 Experiments Using Texture Features
97(1)
6.4.3 Experiments on Fusion of Geometric and Texture Features
98(1)
6.5 Summary
99(4)
Appendix 1
100(1)
References
101(2)
7 Optimal Feature Set for Facial Beauty Analysis
103(20)
7.1 Introduction
103(1)
7.2 Feature Extraction
104(4)
7.2.1 Ratio Features
105(1)
7.2.2 Shape
105(1)
7.2.3 Eigenface
105(1)
7.2.4 AAM
106(1)
7.2.5 Gabor
107(1)
7.2.6 LBP
107(1)
7.2.7 PCANet
107(1)
7.3 Feature Selection
108(1)
7.4 Score Level Fusion and Optimal Feature Set
109(1)
7.5 Experiments Results
110(7)
7.5.1 Data Set and Preprocessing
110(1)
7.5.2 KNN Regression Results
111(2)
7.5.3 Comparison of Regression Methods
113(1)
7.5.4 Feature Selection Results
113(1)
7.5.5 Results of Score Level Fusion and Optimal Feature Set
114(2)
7.5.6 Comparison with Other Works
116(1)
7.6 Summary
117(6)
References
118(5)
Part III Hypotheses on Facial Beauty Perception
8 Examination of Averageness Hypothesis on Large Database
123(20)
8.1 Introduction
123(1)
8.2 Face Shape Space Modeling
124(4)
8.2.1 Perception Function of Facial Beauty
124(1)
8.2.2 Geometric Feature Definition
125(1)
8.2.3 Human Face Shape Space SFS
125(1)
8.2.4 Distance Measurement in SFS
126(1)
8.2.5 Calculation of Average Face Shapes in SFS
127(1)
8.3 Methodology: Quantitative Analysis
128(4)
8.3.1 Automatic Geometric Feature Extraction
128(1)
8.3.2 Automatic Face Deformation
128(3)
8.3.3 Stimuli Generation
131(1)
8.3.4 Perception Experiment Design
131(1)
8.4 Results and Analysis
132(7)
8.4.1 Distribution of Human Face Shapes in SG
132(1)
8.4.2 Effect of Database Sizes on Average Face Shapes
132(2)
8.4.3 Female Versus Male Average Face Shapes
134(1)
8.4.4 Role of Average Face Shapes in Human Facial Beauty
134(5)
8.5 Summary
139(4)
Appendix I
140(1)
Appendix II
141(1)
References
141(2)
9 A New Hypothesis on Facial Beauty Perception
143(24)
9.1 Introduction
143(3)
9.2 The Weighted Averageness (WA) Hypothesis
146(1)
9.3 Empirical Proof of the WA Hypothesis
147(5)
9.3.1 Face Image Dataset
147(1)
9.3.2 Attractiveness Score Regression
148(1)
9.3.3 Test the Hypothesis
149(3)
9.4 Corollary of the Hypothesis and Convex Hull Based Face Beautification
152(6)
9.4.1 Corollary of the WA Hypothesis
152(1)
9.4.2 Convex Hull-Based Face Beautification
152(1)
9.4.3 Results
153(2)
9.4.4 Comparison and Discussion
155(3)
9.5 Compatibility with Other Hypotheses
158(3)
9.5.1 Compatibility with the Averageness Hypothesis
159(1)
9.5.2 Compatibility with the Symmetry Hypothesis
160(1)
9.5.3 Compatibility with the Golden Ratio Hypothesis
160(1)
9.6 Summary
161(6)
References
162(5)
Part IV Computational Models of Facial Beauty
10 Beauty Analysis by Learning Machine and Subspace Extension
167(32)
10.1 Introduction
168(3)
10.1.1 SLFN and ELM
168(2)
10.1.2 Kernel ELM
170(1)
10.1.3 Weighted ELM
170(1)
10.2 Evolutionary Cost-Sensitive Extreme Learning Machine
171(7)
10.2.1 Cost-Sensitive Extreme Learning Machine
172(2)
10.2.2 Evolutionary CSELM
174(1)
10.2.3 Optimization
175(2)
10.2.4 Parameters Setting
177(1)
10.3 Discriminative Subspace Extension: ECSLDA
178(1)
10.4 Multi-modality Human Beauty Data Analysis
179(9)
10.4.1 M2B Database
180(1)
10.4.2 Attractiveness Assessment: Beauty Recognition
181(7)
10.5 Performance Analysis
188(7)
10.5.1 Face Analysis
188(5)
10.5.2 Parameter Sensitivity Analysis
193(1)
10.5.3 Computational Complexity Analysis
194(1)
10.6 Summary
195(4)
References
195(4)
11 Combining a Causal Effect Criterion for Evaluation of Facial Beauty Models
199(18)
11.1 Introduction
199(2)
11.2 Causal Effect Criterion
201(2)
11.3 Facial Beauty Modeling
203(4)
11.3.1 Feature Extraction
203(2)
11.3.2 Manifold Learning and Attractiveness Regression
205(2)
11.3.3 Feature Normalization and Model Causality
207(1)
11.4 Model Based Facial Beauty Manipulation
207(1)
11.5 Experimental Results
208(6)
11.5.1 Results of Attractiveness Manifold Learning
208(2)
11.5.2 Facial Attractiveness Manipulation
210(3)
11.5.3 Quantitative Comparison Under Prediction Performance and Causal Effect Criteria
213(1)
11.6 Summary
214(3)
References
215(2)
12 Data-Driven Facial Beauty Analysis: Prediction, Retrieval and Manipulation
217(20)
12.1 Introduction
217(2)
12.2 Facial Image Preprocessing and Feature Extraction
219(2)
12.2.1 Face Detection and Landmark Extraction
220(1)
12.2.2 Face Registration and Cropping
220(1)
12.2.3 Low-Level Face Representations
221(1)
12.2.4 Soft Biometric Traits
221(1)
12.3 Facial Beauty Modeling
221(1)
12.3.1 Problem Formulation
222(1)
12.3.2 Regression Methods
222(1)
12.4 Facial Beauty Prediction
222(1)
12.5 Beauty-Oriented Face Retrieval
223(1)
12.5.1 Retrieval for Face Recommendation
224(1)
12.5.2 Retrieval for Face Beautification
224(1)
12.6 Facial Beauty Manipulation
224(2)
12.6.1 Exemplar-Based Manipulation
225(1)
12.6.2 Model-Based Manipulation
225(1)
12.7 Experiments
226(6)
12.7.1 Data Set
226(1)
12.7.2 Evaluation of Features for Facial Beauty Prediction
226(1)
12.7.3 Benefit of Soft Biometric Traits
227(1)
12.7.4 Results of Feature Fusion and Selection
227(2)
12.7.5 Results of Beauty-Oriented Face Retrieval
229(1)
12.7.6 Results of Facial Beauty Manipulation
230(2)
12.8 Summary
232(5)
References
233(4)
Part V Application System
13 A Facial Beauty Analysis Simulation System
237(22)
13.1 Introduction
237(3)
13.2 Face Detection
240(3)
13.2.1 Face Landmark
240(1)
13.2.2 Face Image Correction
241(2)
13.3 Facial Beauty Analysis
243(4)
13.3.1 Beauty Analysis by Geometry Features
243(2)
13.3.2 Beauty Analysis by Texture Features
245(1)
13.3.3 Beauty Analysis by Popular Feature Model
245(2)
13.4 Facial Aesthetics Applications
247(3)
13.4.1 Facial Beauty Prediction Model
247(1)
13.4.2 Facial Beautification Model
248(2)
13.5 System Design for Facial Beauty Simulation
250(7)
13.5.1 System Interface
250(2)
13.5.2 Data Collection and Database
252(1)
13.5.3 Experimental Results
253(4)
13.6 Summary
257(2)
References
257(2)
14 Book Review and Future Work
259(6)
14.1 Overview of the Book
259(1)
14.2 Challenges and Future Work
260(5)
Index 265