An Introduction to Object Recognition (eBook)
XVIII, 202 Seiten
Springer London (Verlag)
978-1-84996-235-3 (ISBN)
Object recognition has been an area of extensive research for a long time. During the last decades, a large number of algorithms have been proposed. This is due to the fact that, at a closer look, "e;object recognition"e; is an umbrella term for different algorithms designed for a wide variety of applications, where each application has its specific requirements and constraints. This book demonstrates the diversity of applications and highlights some important algorithm classes by presenting representative example algorithms for each class.This book is written in a tutorial style and is therefore suitable as an introduction into the field of object recognition for interested readers who are not yet experts. The presentation of each algorithm focuses on the main idea, which is described in detail, and avoids extensive usage of mathematics. Graphic illustrations of the algorithm flow facilitate understanding.The algorithms presented are classified according to the following categories: global approaches, transformation-search-based methods, geometrical model driven methods, 3D object recognition schemes, flexible contour fitting algorithms and feature-based methods. Typical example algorithms are presented for each of the categories.
Preface 6
Acknowledgments 9
Contents 10
Abbreviations 14
1 Introduction 15
1.1 Overview 15
1.2 Areas of Application 17
1.3 Requirements and Constraints 18
1.4 Categorization of Recognition Methods 21
References 24
2 Global Methods 25
2.1 2D Correlation 25
2.1.1 Basic Approach 25
2.1.1.1 Main Idea 25
2.1.1.2 Example 27
2.1.1.3 Pseudocode 28
2.1.1.4 Rating 28
2.1.2 Variants 29
2.1.2.1 Variant 1: Preprocessing 29
2.1.2.2 Variant 2: Subsampling/Image Pyramids 31
2.1.3 Phase-Only Correlation (POC) 32
2.1.3.1 Example 33
2.1.3.2 Pseudocode 34
2.1.4 Shape-Based Matching 34
2.1.4.1 Main Idea 34
2.1.4.2 Example 35
2.1.4.3 Pseudocode 35
2.1.4.4 Rating 36
2.1.5 Comparison 36
2.2 Global Feature Vectors 38
2.2.1 Main Idea 38
2.2.2 Classification 38
2.2.3 Rating 39
2.2.4 Moments 39
2.2.4.1 Main Idea 39
2.2.4.2 Example 40
2.2.5 Fourier Descriptors 41
2.2.5.1 Main Idea 41
2.2.5.2 Example 41
2.2.5.3 Modifications 43
2.2.5.4 Pseudocode 44
2.3 Principal Component Analysis (PCA) 45
2.3.1 Main Idea 45
2.3.2 Pseudocode 48
2.3.3 Rating 49
2.3.4 Example 49
2.3.5 Modifications 51
References 52
3 Transformation-Search Based Methods 54
3.1 Overview 54
3.2 Transformation Classes 55
3.3 Generalized Hough Transform 57
3.3.1 Main Idea 57
3.3.2 Training Phase 57
3.3.3 Recognition Phase 58
3.3.4 Pseudocode 59
3.3.5 Example 60
3.3.6 Rating 62
3.3.7 Modifications 63
3.4 The Hausdorff Distance 64
3.4.1 Basic Approach 64
3.4.1.1 Main Idea 64
3.4.1.2 Recognition Phase 65
3.4.1.3 Pseudocode 68
3.4.1.4 Example 70
3.4.1.5 Rating 71
3.4.2 Variants 72
3.4.2.1 Variant 1: Generalized Hausdorff Distance Generalized Hausdorff distance 72
3.4.2.2 Variant 2: 3D Hausdorff Distance 72
3.4.2.3 Variant 3: Chamfer Matching 73
3.5 Speedup by Rectangular Filters and Integral Images 73
3.5.1 Main Idea 73
3.5.2 Filters and Integral Images 74
3.5.3 Classification 76
3.5.4 Pseudocode 78
3.5.5 Example 79
3.5.6 Rating 80
References 80
4 Geometric Correspondence-Based Approaches 82
4.1 Overview 82
4.2 Feature Types and Their Detection 83
4.2.1 Geometric Primitives 84
4.2.1.1 Polygonal Approximation 84
4.2.1.2 Approximation with Line Segments and Circular Arcs 84
4.2.2 Geometric Filters 87
4.3 Graph-Based Matching 88
4.3.1 Geometrical Graph Match 88
4.3.1.1 Main Idea 88
4.3.1.2 Recognition Phase 89
4.3.1.3 Pseudocode 91
4.3.1.4 Example 92
4.3.1.5 Rating 92
4.3.2 Interpretation Trees 93
4.3.2.1 Main Idea 93
4.3.2.2 Recognition Phase 94
4.3.2.3 Pseudocode 97
4.3.2.4 Example 98
4.3.2.5 Rating 99
4.4 Geometric Hashing 100
4.4.1 Main Idea 100
4.4.2 Speedup by Pre-processing 101
4.4.3 Recognition Phase 102
4.4.4 Pseudocode 103
4.4.5 Rating 104
4.4.6 Modifications 104
References 105
5 Three-Dimensional Object Recognition 107
5.1 Overview 107
5.2 The SCERPO System: Perceptual Grouping 109
5.2.1 Main Idea 109
5.2.2 Recognition Phase 110
5.2.3 Example 111
5.2.4 Pseudocode 111
5.2.5 Rating 112
5.3 Relational Indexing 113
5.3.1 Main Idea 113
5.3.2 Teaching Phase 114
5.3.3 Recognition Phase 116
5.3.4 Pseudocode 117
5.3.5 Example 118
5.3.6 Rating 120
5.4 LEWIS: 3D Recognition of Planar Objects 120
5.4.1 Main Idea 120
5.4.2 Invariants 121
5.4.3 Teaching Phase 123
5.4.4 Recognition Phase 124
5.4.5 Pseudocode 125
5.4.6 Example 126
5.4.7 Rating 127
References 128
6 Flexible Shape Matching 129
6.1 Overview 129
6.2 Active Contour Models/Snakes 130
6.2.1 Standard Snake 130
6.2.1.1 Main Idea 130
6.2.1.2 Optimization 131
6.2.1.3 Example 132
6.2.1.4 Rating 133
6.2.2 Gradient Vector Flow Snake 134
6.2.2.1 Main Idea 134
6.2.2.2 Pseudocode 135
6.2.2.3 Example 136
6.2.2.4 Rating 137
6.3 The Contracting Curve Density Algorithm (CCD) 138
6.3.1 Main Idea 138
6.3.2 Optimization 140
6.3.3 Example 141
6.3.4 Pseudocode 142
6.3.5 Rating 142
6.4 Distance Measures for Curves 143
6.4.1 Turning Functions 143
6.4.1.1 Main Idea 143
6.4.1.2 Example 145
6.4.1.3 Pseudocode 146
6.4.1.4 Rating 147
6.4.2 Curvature Scale Space (CSS) 147
6.4.2.1 Main Idea 147
6.4.2.2 Pseudocode 150
6.4.2.3 Rating 151
6.4.3 Partitioning into Tokens 151
6.4.3.1 Main Idea 151
6.4.3.2 Example 153
6.4.3.3 Pseudocode 154
6.4.3.4 Rating 155
References 155
7 Interest Point Detection and Region Descriptors 156
7.1 Overview 156
7.2 Scale Invariant Feature Transform (SIFT) 158
7.2.1 SIFT Interest Point Detector: The DoG Detector 158
7.2.1.1 Main Idea 158
7.2.1.2 Example 159
7.2.2 SIFT Region Descriptor 160
7.2.2.1 Main Idea 160
7.2.2.2 Example 161
7.2.3 Object Recognition with SIFT 161
7.2.3.1 Training Phase 161
7.2.3.2 Recognition Phase 161
7.2.3.3 Pseudocode 163
7.2.3.4 Example 164
7.2.3.5 Rating 165
7.2.3.6 Modifications 166
7.3 Variants of Interest Point Detectors 166
7.3.1 Harris and Hessian-Based Detectors 167
7.3.1.1 Rating 168
7.3.2 The FAST Detector for Corners 168
7.3.2.1 Rating 169
7.3.3 Maximally Stable Extremal Regions (MSER) 169
7.3.3.1 Rating 170
7.3.4 Comparison of the Detectors 170
7.4 Variants of Region Descriptors 171
7.4.1 Variants of the SIFT Descriptor 171
7.4.2 Differential-Based Filters 173
7.4.3 Moment Invariants 174
7.4.4 Rating of the Descriptors 175
7.5 Descriptors Based on Local Shape Information 175
7.5.1 Shape Contexts 175
7.5.1.1 Main Idea 175
7.5.1.2 Recognition Phase 176
7.5.1.3 Pseudocode 178
7.5.1.4 Rating 179
7.5.2 Variants 179
7.5.2.1 Labeled Distance Sets 179
7.5.2.2 Shape Similarity Based on Contour Parts 180
7.6 Image Categorization 181
7.6.1 Appearance-Based ''Bag-of-Features'' Approach 181
7.6.1.1 Main Idea 181
7.6.1.2 Example 182
7.6.1.3 Modifications 183
7.6.1.4 Spatial Pyramid Matching 184
7.6.2 Categorization with Contour Information 185
7.6.2.1 Main Idea 186
7.6.2.2 Training Phase 187
7.6.2.3 Recognition Phase 189
7.6.2.4 Example 189
7.6.2.5 Pseudocode 190
7.6.2.6 Rating 191
References 192
8 Summary 194
Appendix A Edge Detection 198
A.1 Gradient Calculation 199
A.2 Canny Edge Detector 200
References 202
Appendix B Classification 203
B.1 Nearest-Neighbor Classification 203
B.2 Mahalanobis Distance 204
B.3 Linear Classification 205
B.4 Bayesian Classification 206
B.5 Other Schemes 206
References 207
Index 208
| Erscheint lt. Verlag | 23.7.2010 |
|---|---|
| Reihe/Serie | Advances in Computer Vision and Pattern Recognition | Advances in Computer Vision and Pattern Recognition |
| Zusatzinfo | XVIII, 202 p. |
| Verlagsort | London |
| Sprache | englisch |
| Themenwelt | Informatik ► Grafik / Design ► Digitale Bildverarbeitung |
| Informatik ► Theorie / Studium ► Künstliche Intelligenz / Robotik | |
| Schlagworte | 3D • algorithms • Appearance-based Recognition • Cognition • computer vision • Electronics • Image Processing • Image Retrieval • Object Alignment • Object Pose • Object recognition • Optical Inspection • Position Measurement • Scene Categorization |
| ISBN-10 | 1-84996-235-9 / 1849962359 |
| ISBN-13 | 978-1-84996-235-3 / 9781849962353 |
| Haben Sie eine Frage zum Produkt? |
PDF (Ohne DRM)Digital Rights Management: ohne DRM
Dieses eBook enthält kein DRM oder Kopierschutz. Eine Weitergabe an Dritte ist jedoch rechtlich nicht zulässig, weil Sie beim Kauf nur die Rechte an der persönlichen Nutzung erwerben.
Dateiformat: PDF (Portable Document Format)
Mit einem festen Seitenlayout eignet sich die PDF besonders für Fachbücher mit Spalten, Tabellen und Abbildungen. Eine PDF kann auf fast allen Geräten angezeigt werden, ist aber für kleine Displays (Smartphone, eReader) nur eingeschränkt geeignet.
Systemvoraussetzungen:
PC/Mac: Mit einem PC oder Mac können Sie dieses eBook lesen. Sie benötigen dafür einen PDF-Viewer - z.B. den Adobe Reader oder Adobe Digital Editions.
eReader: Dieses eBook kann mit (fast) allen eBook-Readern gelesen werden. Mit dem amazon-Kindle ist es aber nicht kompatibel.
Smartphone/Tablet: Egal ob Apple oder Android, dieses eBook können Sie lesen. Sie benötigen dafür einen PDF-Viewer - z.B. die kostenlose Adobe Digital Editions-App.
Buying eBooks from abroad
For tax law reasons we can sell eBooks just within Germany and Switzerland. Regrettably we cannot fulfill eBook-orders from other countries.
aus dem Bereich
