Deep Learning in Object Detection and Recognition (eBook)
XVI, 224 Seiten
Springer Singapore (Verlag)
978-981-10-5152-4 (ISBN)
This book discusses recent advances in object detection and recognition using deep learning methods, which have achieved great success in the field of computer vision and image processing. It provides a systematic and methodical overview of the latest developments in deep learning theory and its applications to computer vision, illustrating them using key topics, including object detection, face analysis, 3D object recognition, and image retrieval.
The book offers a rich blend of theory and practice. It is suitable for students, researchers and practitioners interested in deep learning, computer vision and beyond and can also be used as a reference book. The comprehensive comparison of various deep-learning applications helps readers with a basic understanding of machine learning and calculus grasp the theories and inspires applications in other computer vision tasks.
?Xiaoyue Jiang received her Ph.D. degree in Computer Science and Technology from Northwestern Polytechnical University in 2006. From Xiaoyue Jiang received her Ph.D. degree in Computer Science and Technology from Northwestern Polytechnical University in 2006. From 2006 to 2012, she has worked in Vrije University of Brussels (Belgium), University of Birmingham (UK) and Queen's University of Belfast (UK) as assistant and associated research fellow, respectively. She has worked as associated professor at Northwestern Polytechnical University since 2012. Her research interests includes computer vision, image processing and pattern recognition. She has published more than 50 research papers and is currently senior fellow and secretary of Shaanxi Society of Image and Graphics.
Abdenour Hadid is an adjunct professor at the Center for Machine Vision and Signal Analysis at University of Oulu. He is the chairman of the Pattern Recognition Society of Finland. His research interests include biometrics and facial image analysis, local descriptors, machine learning and human-machine interaction. He has authored over 140< articles in different forums and coauthored a very popular Springer Book on Computer Vision Using Local Binary Patterns in 2011.
Yanwei Pang received his Ph.D. degree in Electronic Engineering from the University of Science and Technology of China (USTC) in 2004. Currently, he is a professor at the School of Electronic Information Engineering, Tianjin University, China. He is also the founding director of the Visual Pattern Analysis Laboratory of Tianjin University. His research interests include deep convolutional neural networks, pattern recognition, machine learning, computer vision and digital image processing. He has authored more than 100 scientific papers, 24 of which were published in IEEE Transactions.
Eric Granger earned his Ph.D. in EE from the Poly-technique Montréal in 2001, and worked as a defense scientist at DRDC-Ottawa (1999-2001), and in R&D with Mitel Networks (2001-04). He joined the École de Technologie Supérieure (Université du Québec), Montreal, in 2004, where he is presently full professor and director of LIVIA, a research laboratory on computer vision and artificial intelligence. His research focuses on adaptive pattern recognition, machine learning, computer vision and computational intelligence.
Xiaoyi Feng received her Ph.D. degree in Electronics and Information from Northwestern Polytechnical University in 2001. She is currently a professor and vice dean of the School of Electronics and Information, Northwestern Polytechnical University, and the vice director of the key laboratory of Ministry of Education 'Aerospace electronics information perception and photoelectric control'. Her research interests include image processing, pattern recognition, computer vision, radar imaging, embedded system design and applications. She is the executive director of Shaanxi Society of Image and Graphics, and senior member of the China Society of Electronics.
This book discusses recent advances in object detection and recognition using deep learning methods, which have achieved great success in the field of computer vision and image processing. It provides a systematic and methodical overview of the latest developments in deep learning theory and its applications to computer vision, illustrating them using key topics, including object detection, face analysis, 3D object recognition, and image retrieval. The book offers a rich blend of theory and practice. It is suitable for students, researchers and practitioners interested in deep learning, computer vision and beyond and can also be used as a reference book. The comprehensive comparison of various deep-learning applications helps readers with a basic understanding of machine learning and calculus grasp the theories and inspires applications in other computer vision tasks.
Preface 5
Contents 9
Acronyms 13
An Overview of Deep Learning 17
1 Brief Introduction 17
2 Basic Types 19
2.1 Stacked Autoencoders (SAEs) 20
2.2 Deep Belief Networks (DBNs) 21
2.3 Convolutional Neural Networks (CNNs) 22
2.4 Recurrent Neural Networks (RNNs) 24
2.5 Generative Adversarial Nets (GANs) 25
3 Practical Applications 27
3.1 Audio Data 27
3.2 Image Data 28
3.3 Text Data 29
4 Existing Challenges 30
4.1 Theory Challenges 30
4.2 Engineering Challenges 31
5 Conclusions 31
References 32
Deep Learning in Object Detection 35
1 Introduction 35
2 The CNN Architectures of Object Detection 37
2.1 Two-Stage Methods for Deep Object Detection 37
2.2 One-Stage Methods for Deep Object Detection 46
3 Pedestrian Detection 50
3.1 Handcrafted Feature-Based Methods for Pedestrian Detection 50
3.2 CNN-Based Methods for Pedestrian Detection 56
4 Challenges of Object Detection 62
4.1 Scale Variation Problem 62
4.2 Occlusion Problem 68
4.3 Deformation Problem 69
References 70
Deep Learning in Face Recognition Across Variations in Pose and Illumination 74
1 Introduction 74
2 Pose-Invariant Face Recognition 76
2.1 Invariant Representation 76
2.1.1 Engineering Designed Features 76
2.1.2 Learning-Based Features 79
2.2 Synthesis-Based Methods 87
2.2.1 2D-Based Synthesis Methods 87
2.2.2 3D-Based Synthesis Methods 89
3 Illumination-Invariant Face Recognition 89
3.1 Image Processing-Based Methods 89
3.2 Invariant Feature-Based Methods 91
3.3 Illumination Model-Based Method 93
4 Multi-stream Convolutional Neural Networks 96
4.1 Root Convolutional Layer 96
4.2 Multi-hierarchical Local Feature 98
4.3 Training 99
5 Experiments 99
5.1 Dataset 99
5.2 Recognition Across Poses and Illumination 100
6 Conclusion 101
References 102
Face Anti-spoofing via Deep Local Binary Pattern 106
1 Introduction 106
2 Related Work 108
3 Proposed Method 110
3.1 CNN Training 111
3.2 Color Spaces 111
3.3 Local Binary Pattern (LBP) 111
3.4 Concatenating the LBP 113
3.5 Classification 114
4 Experimental Data and Setup 114
4.1 Experimental Data 114
4.1.1 Replay-Attack 114
4.1.2 CASIA-FA 115
4.2 Experimental Setups 116
4.2.1 Evaluation Protocol 116
4.2.2 Data Processing 116
4.2.3 Intra Test and Cross Test 117
5 Results and Discussion 117
5.1 Impact of Different Color Spaces 117
5.1.1 Intra Test 117
5.1.2 Cross Test 120
5.2 Concatenating Different Color Spaces 120
5.2.1 Intra Test 120
5.2.2 Cross Test 121
5.3 Comparison Against State-of-the-Art Methods 121
6 Conclusion 123
References 125
Kinship Verification Based on Deep Learning 127
1 Introduction 127
2 Related Work 128
2.1 Methods Based on Features 129
2.2 Methods Using Metric Learning 130
2.3 Other Methods 130
3 Image-Based Kinship Verification 131
3.1 Methodology 131
3.2 Experimental Analysis 135
4 Video-Based Kinship Verification 136
4.1 Methodology 137
4.2 Experimental Analysis 140
5 Conclusion 144
References 144
Deep Learning Architectures for Face Recognition in VideoSurveillance 147
1 Introduction 148
2 Background of Video-Based FR Through Deep Learning 149
3 Deep Learning Architectures for FR in VS 151
3.1 Deep CNNs Using Triplet-Loss 151
3.1.1 Cross-Correlation Matching CNN 151
3.1.2 Trunk-Branch Ensemble CNN 155
3.1.3 HaarNet 156
3.2 Deep CNNs Using Autoencoder 161
4 Performance Evaluation 164
5 Conclusion and Future Directions 165
References 166
Deep Learning for 3D Data Processing 169
1 Introduction 170
2 Related Works 172
2.1 Knowledge-Based 3D Local Features 172
2.2 Deep Learning for 3D Shapes With Raw Features 172
2.3 Restricted Boltzmann Machines (RBM) and Deep Belief Network (DBN) 173
2.4 Convolutional RBM (CRBM) and Convolutional DBN (CDBN) 174
2.5 Details of CRBM and CDBN 174
3 Circle Convolutional RBM (CCRBM) 176
3.1 Circle Convolution 176
3.2 Projection Distance Distribution (PDD) 180
3.3 Example of Circle Convolution and PDD Computation 180
3.4 Elimination of the Initial Location Ambiguity 181
3.5 The Structure of CCRBM 183
3.6 Circle Convolutional DBN (CCDBN) 186
4 Experimental Setup 187
4.1 Global Shape Retrieval 187
4.2 Partial Shape Retrieval 188
4.3 Shape Correspondence 188
4.4 The Setup of Parameters for CCRBM 189
5 Results and Analysis 193
5.1 Global Shape Retrieval 193
5.2 Partial Shape Retrieval 194
5.3 Shape Correspondence 195
5.4 Significance and Analysis 196
5.5 Limitation and Future Work 197
6 Conclusion 197
References 198
Deep Learning-Based Descriptors for Object Instance Search 202
1 Introduction 203
2 Related Work 204
3 Compact Invariant Deep Descriptors 207
3.1 Restricted Boltzmann Machine for Hashing 208
3.1.1 Method 208
3.1.2 Evaluation Framework 212
3.1.3 Experimental Results 213
3.2 Dual-Margin Siamese Fine-Tuning 215
3.2.1 Method 217
3.2.2 Evaluation Framework 219
3.2.3 Experimental Results 219
3.3 Nested Invariance Pooling 221
3.3.1 I-Theory in a Nutshell 221
3.3.2 CNNs Are I-Theory Compliant Networks 222
3.3.3 Multigroup-Invariant CNN Descriptors 222
3.3.4 Evaluation Framework 225
3.3.5 Experimental Results 226
3.4 Hashing with Invariant Descriptors 229
4 Conclusions and Future Works 232
References 233
| Erscheint lt. Verlag | 18.11.2019 |
|---|---|
| Zusatzinfo | XVI, 224 p. 113 illus., 92 illus. in color. |
| Sprache | englisch |
| Themenwelt | Informatik ► Datenbanken ► Data Warehouse / Data Mining |
| Informatik ► Grafik / Design ► Digitale Bildverarbeitung | |
| Informatik ► Theorie / Studium ► Künstliche Intelligenz / Robotik | |
| Schlagworte | Deep learning • expression recognition • face recognition • Image Processing • Image understanding • Object detection • Object recognition |
| ISBN-10 | 981-10-5152-6 / 9811051526 |
| ISBN-13 | 978-981-10-5152-4 / 9789811051524 |
| Haben Sie eine Frage zum Produkt? |
PDF (Wasserzeichen)Größe: 10,3 MB
DRM: Digitales Wasserzeichen
Dieses eBook enthält ein digitales Wasserzeichen und ist damit für Sie personalisiert. Bei einer missbräuchlichen Weitergabe des eBooks an Dritte ist eine Rückverfolgung an die Quelle möglich.
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.
Zusätzliches Feature: Online Lesen
Dieses eBook können Sie zusätzlich zum Download auch online im Webbrowser lesen.
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
