Learn how to apply cognitive principles to the problems of computer vision
Computational Models for Cognitive Vision formulates the computational models for the cognitive principles found in biological vision, and applies those models to computer vision tasks. Such principles include perceptual grouping, attention, visual quality and aesthetics, knowledge-based interpretation and learning, to name a few. The author’s ultimate goal is to provide a framework for creation of a machine vision system with the capability and versatility of the human vision.
Written by Dr. Hiranmay Ghosh, the book takes readers through the basic principles and the computational models for cognitive vision, Bayesian reasoning for perception and cognition, and other related topics, before establishing the relationship of cognitive vision with the multi-disciplinary field broadly referred to as “artificial intelligence”. The principles are illustrated with diverse application examples in computer vision, such as computational photography, digital heritage and social robots. The author concludes with suggestions for future research and salient observations about the state of the field of cognitive vision.
Other topics covered in the book include:
· knowledge representation techniques
· evolution of cognitive architectures
· deep learning approaches for visual cognition
Undergraduate students, graduate students, engineers, and researchers interested in cognitive vision will consider this an indispensable and practical resource in the development and study of computer vision.
Table of Contents
About the Author ix
Acknowledgments xi
Preface xiii
Acronyms xv
1 Introduction 1
1.1 What Is Cognitive Vision 2
1.2 Computational Approaches for Cognitive Vision 3
1.3 A Brief Review of Human Vision System 4
1.4 Perception and Cognition 6
1.5 Organization of the Book 7
2 Early Vision9
2.1 Feature Integration Theory 9
2.2 Structure of Human Eye 10
2.3 Lateral Inhibition 13
2.4 Convolution: Detection of Edges and Orientations 14
2.5 Color and Texture Perception 17
2.6 Motion Perception 19
2.6.1 Intensity-Based Approach 19
2.6.2 Token-Based Approach 20
2.7 Peripheral Vision 21
2.8 Conclusion 24
3 Bayesian Reasoning for Perception and Cognition 25
3.1 Reasoning Paradigms 26
3.2 Natural Scene Statistics 27
3.3 Bayesian Framework of Reasoning 28
3.4 Bayesian Networks 32
3.5 Dynamic Bayesian Networks 34
3.6 Parameter Estimation 36
3.7 On Complexity of Models and Bayesian Inference 38
3.8 Hierarchical Bayesian Models 39
3.9 Inductive Reasoning with Bayesian Framework 41
3.9.1 Inductive Generalization 41
3.9.2 Taxonomy Learning 45
3.9.3 Feature Selection 46
3.10 Conclusion 47
4 Late Vision 51
4.1 Stereopsis and Depth Perception 51
4.2 Perception of Visual Quality 53
4.3 Perceptual Grouping 55
4.4 Foreground-Background Separation 59
4.5 Multi-stability 60
4.6 Object Recognition 61
4.6.1 In-Context Object Recognition 62
4.6.2 Synthesis of Bottom-Up and Top-Down Knowledge 64
4.6.3 Hierarchical Modeling 65
4.6.4 One-Shot Learning 66
4.7 Visual Aesthetics 67
4.8 Conclusion 69
5 Visual Attention 71
5.1 Modeling of Visual Attention 72
5.2 Models for Visual Attention 75
5.2.1 Cognitive Models 75
5.2.2 Information-Theoretic Models 77
5.2.3 Bayesian Models 78
5.2.4 Context-Based Models 79
5.2.5 Object-Based Models 81
5.3 Evaluation 82
5.4 Conclusion 84
6 Cognitive Architectures 87
6.1 Cognitive Modeling 88
6.1.1 Paradigms for Modeling Cognition 88
6.1.2 Levels of Abstraction 91
6.2 Desiderata for Cognitive Architectures 92
6.3 Memory Architecture 94
6.4 Taxonomies of Cognitive Architectures 97
6.5 Review of Cognitive Architectures 99
6.5.1 STAR: Selective Tuning Attentive Reference 100
6.5.2 LIDA: Learning Intelligent Distribution Agent 102
6.6 Biologically Inspired Cognitive Architectures 105
6.7 Conclusions 106
7 Knowledge Representation for Cognitive Vision 109
7.1 Classicist Approach to Knowledge Representation 109
7.1.1 First Order Logic 111
7.1.2 Semantic Networks 113
7.1.3 Frame-Based Representation 114
7.2 Symbol Grounding Problem 117
7.3 Perceptual Knowledge 118
7.3.1 Representing Perceptual Knowledge 119
7.3.2 Structural Description of Scenes 120
7.3.3 Qualitative Spatial and Temporal Relations 122
7.3.4 Inexact Spatiotemporal Relations 124
7.4 Unifying Conceptual and Perceptual Knowledge 127
7.5 Knowledge-Based Visual Data Processing 128
7.6 Conclusion 129
8 Deep Learning for Visual Cognition 131
8.1 A Brief Introduction to Deep Neural Networks 132
8.1.1 Fully Connected Networks 132
8.1.2 Convolutional Neural Networks 134
8.1.3 Recurrent Neural Networks 137
8.1.4 Siamese Networks 140
8.1.5 Graph Neural Networks 140
8.2 Modes of Learning with DNN 142
8.2.1 Supervised Learning 142
8.2.1.1 Image Segmentation 142
8.2.1.2 Object Detection 144
8.2.2 Unsupervised Learning with Generative Networks 144
8.2.3 Meta-Learning: Learning to Learn 146
8.2.3.1 Reinforcement Learning 148
8.2.3.2 One-Shot and Few-Shot Learning 148
8.2.3.3 Zero-Shot Learning 150
8.2.3.4 Incremental Learning 150
8.2.4 Multi-task Learning 152
8.3 Visual Attention 154
8.3.1 Recurrent Attention Models 155
8.3.2 Recurrent Attention Model for Video 158
8.4 Bayesian Inferencing with Neural Networks 159
8.5 Conclusion 160
9 Applications of Visual Cognition 163
9.1 Computational Photography 163
9.1.1 Color Enhancement 164
9.1.2 Intelligent Cropping 166
9.1.3 Face Beautification 167
9.2 Digital Heritage 168
9.2.1 Digital Restoration of Images 168
9.2.2 Curating Dance Archives 170
9.3 Social Robots 172
9.3.1 Dynamic and Shared Spaces 173
9.3.2 Recognition of Visual Cues 174
9.3.3 Attention to Socially Relevant Signals 175
9.4 Content Re-purposing 177
9.5 Conclusion 179
10 Conclusion 181
10.1 “What Is Cognitive Vision” Revisited 181
10.2 Divergence of Approaches 183
10.3 Convergence on the Anvil? 185
References 187
Index 215
