Modern Machine Learning Techniques and Their Applications in Cartoon Animation Research

Inbunden, Engelska, 2013

Del 4 i serien IEEE Press Series on Systems Science and Engineering

1 188 kr

Beställningsvara. Skickas inom 5-8 vardagar. Fri frakt över 249 kr.

Beskrivning

The integration of machine learning techniques and cartoon animation research is fast becoming a hot topic. This book helps readers learn the latest machine learning techniques, including patch alignment framework; spectral clustering, graph cuts, and convex relaxation; ensemble manifold learning; multiple kernel learning; multiview subspace learning; and multiview distance metric learning. It then presents the applications of these modern machine learning techniques in cartoon animation research. With these techniques, users can efficiently utilize the cartoon materials to generate animations in areas such as virtual reality, video games, animation films, and sport simulations

Produktinformation

Utgivningsdatum:2013-04-26
Mått:163 x 244 x 17 mm
Vikt:454 g
Format:Inbunden
Språk:Engelska
Serie:IEEE Press Series on Systems Science and Engineering
Antal sidor:208
Förlag:John Wiley & Sons Inc
ISBN:9781118115145

Utforska kategorier

Mer om författaren

JUN YU, PhD, is an Associate Professor in the Computer Science Department, School of Information Science and Engineering, Xiamen University, Xiamen, China. His current research interests include computer graphics, computer visions, and machine learning. He has authored or coauthored more than thirty scientific articles in journals including IEEE T-IP, IEEE TSMC-B, and Pattern Recognition.DACHENG TAO, PhD, is Professor of Computer Science with the Centre for Quantum Computation & Intelligent Systems and the Faculty of Engineering & Information Technology, University of Technology, Sydney, Australia. His research applies statistics and mathematics to data analysis problems in computer vision, data mining, machine learning, multimedia, and video surveillance. He has authored more than 100 scientific articles.

Innehållsförteckning

Preface xi1 Introduction 11.1 Perception 21.2 Overview of Machine Learning Techniques 21.2.1 Manifold Learning 31.2.2 Semi-supervised Learning 51.2.3 Multiview Learning 81.2.4 Learning-based Optimization 91.3 Recent Developments in Computer Animation 111.3.1 Example-Based Motion Reuse 111.3.2 Physically Based Computer Animation 261.3.3 Computer-Assisted Cartoon Animation 331.3.4 Crowd Animation 421.3.5 Facial Animation 511.4 Chapter Summary 602 Modern Machine Learning Techniques 632.1 A Unified Framework for Manifold Learning 652.1.1 Framework Introduction 652.1.2 Various Manifold Learning Algorithm Unifying 672.1.3 Discriminative Locality Alignment 692.1.4 Discussions 712.2 Spectral Clustering and Graph Cut 712.2.1 Spectral Clustering 722.2.2 Graph Cut Approximation 762.3 Ensemble Manifold Learning 812.3.1 Motivation for EMR 812.3.2 Overview of EMR 812.3.3 Applications of EMR 842.4 Multiple Kernel Learning 862.4.1 A Unified Mulitple Kernel Learning Framework 872.4.2 SVM with Multiple Unweighted-Sum Kernels 892.4.3 QCQP Multiple Kernel Learning 892.5 Multiview Subspace Learning 902.5.1 Approach Overview 902.5.2 Techinique Details 902.5.3 Alternative Optimization Used in PA-MSL 932.6 Multiview Distance Metric Learning 942.6.1 Motivation for MDML 942.6.2 Graph-Based Semi-supervised Learning 952.6.3 Overview of MDML 952.7 Multi-task Learning 982.7.1 Introduction of Structural Learning 992.7.2 Hypothesis Space Selection 1002.7.3 Algorithm for Multi-task Learning 1012.7.4 Solution by Alternative Optimization 1022.8 Chapter Summary 1033 Animation Research: A Brief Introduction 1053.1 Traditional Animation Production 1073.1.1 History of Traditional Animation Production 1073.1.2 Procedures of Animation Production 1083.1.3 Relationship Between Traditional Animation and Computer Animation 1093.2 Computer-Assisted Systems 1103.2.1 Computer Animation Techniques 1113.3 Cartoon Reuse Systems for Animation Synthesis 1173.3.1 Cartoon Texture for Animation Synthesis 1183.3.2 Cartoon Motion Reuse 1203.3.3 Motion Capture Data Reuse in Cartoon Characters 1223.4 Graphical Materials Reuse: More Examples 1243.4.1 Video Clips Reuse 1243.4.2 Motion Captured Data Reuse by Motion Texture 1263.4.3 Motion Capture Data Reuse by Motion Graph 1273.5 Chapter Summary 1294 Animation Research: Modern Techniques 1314.1 Automatic Cartoon Generation with Correspondence Construction 1314.1.1 Related Work in Correspondence Construction 1324.1.2 Introduction of the Semi-supervised Correspondence Construction 1334.1.3 Stroke Correspondence Construction via Stroke Reconstruction Algorithm 1384.1.4 Simulation Results 1414.2 Cartoon Characters Represented by Multiple Features 1464.2.1 Cartoon Character Extraction 1474.2.2 Color Histogram 1484.2.3 Hausdorff Edge Feature 1484.2.4 Motion Feature 1504.2.5 Skeleton Feature 1514.2.6 Complementary Characteristics of Multiview Features 1534.3 Graph-based Cartoon Clips Synthesis 1544.3.1 Graph Model Construction 1554.3.2 Distance Calculation 1554.3.3 Simulation Results 1564.4 Retrieval-based Cartoon Clips Synthesis 1614.4.1 Constrained Spreading Activation Network 1624.4.2 Semi-supervised Multiview Subspace Learning 1654.4.3 Simulation Results 1684.5 Chapter Summary 173References 174Index 195