Classification, Parameter Estimation and State Estimation (eBook)

An Engineering Approach Using MATLAB

Bangjun Lei, Guangzhu Xu, Ming Feng, Yaobin Zou, Ferdinand van der Heijden, Dick de Ridder, David M. J. Tax (Autoren)

eBook Download: PDF

2017 | 2. Auflage
John Wiley & Sons (Verlag)
978-1-119-15244-6 (ISBN)

Infos

A practical introduction to intelligent computer vision theory, design, implementation, and technology

The past decade has witnessed epic growth in image processing and intelligent computer vision technology. Advancements in machine learning methods-especially among adaboost varieties and particle filtering methods-have made machine learning in intelligent computer vision more accurate and reliable than ever before. The need for expert coverage of the state of the art in this burgeoning field has never been greater, and this book satisfies that need. Fully updated and extensively revised, this 2nd Edition of the popular guide provides designers, data analysts, researchers and advanced post-graduates with a fundamental yet wholly practical introduction to intelligent computer vision. The authors walk you through the basics of computer vision, past and present, and they explore the more subtle intricacies of intelligent computer vision, with an emphasis on intelligent measurement systems. Using many timely, real-world examples, they explain and vividly demonstrate the latest developments in image and video processing techniques and technologies for machine learning in computer vision systems, including: 

• PRTools5 software for MATLAB-especially the latest representation and generalization software toolbox for PRTools5
• Machine learning applications for computer vision, with detailed discussions of contemporary state estimation techniques vs older content of particle filter methods
• The latest techniques for classification and supervised learning, with an emphasis on Neural Network, Genetic State Estimation and other particle filter and AI state estimation methods
• All new coverage of the Adaboost and its implementation in PRTools5.

A valuable working resource for professionals and an excellent introduction for advanced-level students, this 2nd Edition features a wealth of illustrative examples, ranging from basic techniques to advanced intelligent computer vision system implementations. Additional examples and tutorials, as well as a question and solution forum, can be found on a companion website.

Professor  Bangjun Lei, Dr. Guangzhu Xu,  and Dr. Ming Feng are with The Institute of Intelligent Vision and Image Information, China Three Gorges University, China.

Professor Yaobin Zou is an associate professor at China Three Gorges University.
Dr. Ferdinand van der Heijden, Ph.D., is on the faculty of theDepartment of Signals and Systems, University of Twente, Netherlands. 
Professor Dick de Ridder is Professor at the Bioinformatics lab at Wageningen University, Netherlands.

Professor David M. J. Tax, is a researcher with the Pattern Recognition laboratory, Delft University of Technology.

 

 

 

Inhalt

Classification, Parameter Estimation and State Estimation 3
Contents 7
Preface 13
Acknowledgements 16
About the Companion Website 17
1 Introduction 19
1.1 The Scope of the Book 20
1.1.1 Classification 21
1.1.2 Parameter Estimation 22
1.1.3 State Estimation 23
1.1.4 Relations between the Subjects 25
1.2 Engineering 28
1.3 The Organization of the Book 30
1.4 Changes from First Edition 32
1.5 References 33
2 PRTools Introduction 35
2.1 Motivation 35
2.2 Essential Concepts 36
2.3 PRTools Organization Structure and Implementation 40
2.4 Some Details about PRTools 44
2.4.1 Datasets 44
2.4.2 Datafiles 48
2.4.3 Datafiles Help Information 49
2.4.4 Classifiers and Mappings 52
2.4.5 Mappings Help Information 54
2.4.6 How to Write Your Own Mapping 56
2.5 Selected Bibliography 60
3 Detection and Classification 61
3.1 Bayesian Classification 64
3.1.1 Uniform Cost Function and Minimum Error Rate 71
3.1.2 Normal Distributed Measurements Linear and Quadratic Classifiers
3.2 Rejection 80
3.2.1 Minimum Error Rate Classification with Reject Option 81
3.3 Detection: The Two-Class Case 84
3.4 Selected Bibliography 92
4 Parameter Estimation 95
4.1 Bayesian Estimation 97
4.1.1 MMSE Estimation 104
4.1.2 MAP Estimation 105
4.1.3 The Gaussian Case with Linear Sensors 106
4.1.4 Maximum Likelihood Estimation 107
4.1.5 Unbiased Linear MMSE Estimation 109
4.2 Performance Estimators 112
4.2.1 Bias and Covariance 113
4.2.2 The Error Covariance of the Unbiased Linear MMSE Estimator 117
4.3 Data Fitting 118
4.3.1 Least Squares Fitting 119
4.3.2 Fitting Using a Robust Error Norm 122
4.3.3 Regression 125
4.4 Overview of the Family of Estimators 128
4.5 Selected Bibliography 129
5 State Estimation 133
5.1 A General Framework for Online Estimation 135
5.1.1 Models 135
5.1.2 Optimal Online Estimation 141
5.2 Infinite Discrete-Time State Variables 143
5.2.1 Optimal Online Estimation in Linear-Gaussian Systems 143
5.2.2 Suboptimal Solutions for Non-linear Systems 151
5.3 Finite Discrete-Time State Variables 165
5.3.1 Hidden Markov Models 166
5.3.2 Online State Estimation 170
5.3.3 Offline State Estimation 174
5.4 Mixed States and the Particle Filter 181
5.4.1 Importance Sampling 182
5.4.2 Resampling by Selection 184
5.4.3 The Condensation Algorithm 185
5.5 Genetic State Estimation 188
5.5.1 The Genetic Algorithm 188
5.5.2 Genetic State Estimation 194
5.5.3 Computational Issues 195
5.6 State Estimation in Practice 201
5.6.1 System Identification 203
5.6.2 Observability, Controllability and Stability 206
5.6.3 Computational Issues 211
5.6.4 Consistency Checks 214
5.7 Selected Bibliography 219
6 Supervised Learning 225
6.1 Training Sets 226
6.2 Parametric Learning 228
6.2.1 Gaussian Distribution, Mean Unknown 229
6.2.2 Gaussian Distribution, Covariance Matrix Unknown 230
6.2.3 Gaussian Distribution, Mean and Covariance Matrix Both Unknown 231
6.2.4 Estimation of the Prior Probabilities 233
6.2.5 Binary Measurements 234
6.3 Non-parametric Learning 235
6.3.1 Parzen Estimation and Histogramming 236
6.3.2 Nearest Neighbour Classification 241
6.3.3 Linear Discriminant Functions 248
6.3.4 The Support Vector Classifier 255
6.3.5 The Feedforward Neural Network 260
6.4 Adaptive Boosting – Adaboost 263
6.5 Convolutional Neural Networks (CNNs) 267
6.5.1 Convolutional Neural Network Structure 267
6.5.2 Computation and Training of CNNs 269
6.6 Empirical Evaluation 270
6.7 Selected Bibliography 275
7 Feature Extraction and Selection 277
7.1 Criteria for Selection and Extraction 279
7.1.1 Interclass/Intraclass Distance 280
7.1.2 Chernoff–Bhattacharyya Distance 285
7.1.3 Other Criteria 288
7.2 Feature Selection 290
7.2.1 Branch-and-Bound 291
7.2.2 Suboptimal Search 293
7.2.3 Several New Methods of Feature Selection 296
7.2.4 Implementation Issues 305
7.3 Linear Feature Extraction 306
7.3.1 Feature Extraction Based on the Bhattacharyya Distance with Gaussian Distributions 309
7.3.2 Feature Extraction Based on InterIntra Class Distance 314
7.4 References 318
8 Unsupervised Learning 321
8.1 Feature Reduction 322
8.1.1 Principal Component Analysis 322
8.1.2 Multidimensional Scaling 327
8.1.3 Kernel Principal Component Analysis 333
8.2 Clustering 338
8.2.1 Hierarchical Clustering 341
8.2.2 K-Means Clustering 345
8.2.3 Mixture of Gaussians 347
8.2.4 Mixture of probabilistic PCA 353
8.2.5 Self-Organizing Maps 354
8.2.6 Generative Topographic Mapping 360
8.3 References 363
9 Worked Out Examples 367
9.1 Example on Image Classification with PRTools 367
9.1.1 Example on Image Classification 367
9.1.2 Example on Face Classification 372
9.1.3 Example on Silhouette Classification 375
9.2 Boston Housing Classification Problem 379
9.2.1 Dataset Description 379
9.2.2 Simple Classification Methods 381
9.2.3 Feature Extraction 383
9.2.4 Feature Selection 385
9.2.5 Complex Classifiers 386
9.2.6 Conclusions 389
9.3 Time-of-Flight Estimation of an Acoustic Tone Burst 390
9.3.1 Models of the Observed Waveform 392
9.3.2 Heuristic Methods for Determining the ToF 394
9.3.3 Curve Fitting 395
9.3.4 Matched Filtering 397
9.3.5 ML Estimation Using Covariance Models for the Reflections 398
9.3.6 Optimization and Evaluation 403
9.4 Online Level Estimation in a Hydraulic System 410
9.4.1 Linearized Kalman Filte 412
9.4.2 Extended Kalman Filtering 415
9.4.3 Particle Filtering 416
9.4.4 Discussion 421
9.5 References 424
Appendix A Topics Selected from Functional Analysis 425
A.1 Linear Spaces 425
A.1.1 Normed Linear Spaces 427
A.1.2 Euclidean Spaces or Inner Product Spaces 428
A.2 Metric Spaces 430
A.3 Orthonormal Systems and Fourier Series 432
A.4 Linear Operators 434
A.5 Selected Bibliography 437
Appendix B Topics Selected from Linear Algebra and Matrix Theory 439
B.1 Vectors and Matrices 439
B.2 Convolution 442
B.3 Trace and Determinant 444
B.4 Differentiation of Vector and Matrix Functions 445
B.5 Diagonalization of Self-Adjoint Matrices 447
B.6 Singular Value Decomposition (SVD) 450
B.7 Selected Bibliography 453
Appendix C Probability Theory 455
C.1 Probability Theory and Random Variables 455
C.1.1 Moments 458
C.1.2 Poisson Distribution 458
C.1.3 Binomial Distribution 459
C.1.4 Normal Distribution 460
C.1.5 The Chi-Square Distribution 461
C.2 Bivariate Random Variables 462
C.3 Random Vectors 466
C.3.1 Linear Operations on Gaussian Random Vectors 467
C.3.2 Decorrelation 468
C.4 Selected Bibliography 469
Appendix D Discrete-Time Dynamic Systems 471
D.1 Discrete-Time Dynamic Systems 471
D.2 Linear Systems 472
D.3 Linear Time-Invariant Systems 473
D.3.1 Diagonalization of a System 473
D.3.2 Stability 474
D.4 Selected Bibliography 475
Index 477
EULA 483

Produkt-Details

• Erscheint lt. Verlag: 3.3.2017
• Sprache: englisch
• Themenwelt: Mathematik / Informatik ► Mathematik ► Angewandte Mathematik
• Themenwelt: Naturwissenschaften ► Physik / Astronomie ► Mechanik
• Themenwelt: Technik ► Elektrotechnik / Energietechnik
• Themenwelt: Technik ► Maschinenbau
• Schlagworte: AdaBoost • adaboost machine learning in intelligent computer vision • advanced computer vision theory • advances in intelligent computer vision • AI state estimation methods for intelligent computer vision • classification and supervised learning in intelligent computer vision • computer vision • computer vision basics • computer vision theory and practice • Electrical & Electronics Engineering • Elektrotechnik u. Elektronik • FPGA and video processing • genetic state estimation in intelligent computer vision • intelligent computer system design • intelligent computer systems design and implementation • intelligent computer vision • intelligent computer vision design examples • intelligent computer vision examples • intelligent computer vision system design • intelligent computer vision systems development • intelligent computer vision technology • latent support vector machines in intelligent computer vision • latent SVM for intelligent computer vision • machine learning • machine learning in computer vision systems • Mustererkennung • Neural Networks in intelligent computer vision • particle filtering • particle filtering methods in computer vision systems • Pattern Analysis • pattern recognition in intelligent computer vision systems • PRTools5 software for MATLAB • PRTools5 toolbox • Signal Processing • Signalverarbeitung • state-of-the-art computer vision technology • struct support vector machines in intelligent computer vision • struct SVM for intelligent computer vision • Support Vector Machines in intelligent computer vision • SVM for intelligent computer vision • video processing with field programmable gate arrays
• ISBN-10: 1-119-15244-5 / 1119152445
• ISBN-13: 978-1-119-15244-6 / 9781119152446