Recognition and Perception of Images: Fundamentals and Applications

Description

Cover Half-Title Page Series Page Title Page Copyright Page Contents Abstract Preface 1 Perception of Images. Modern Trends 1.1 Visual System 1.1.1 Some Modern Research 1.1.2 Light Perception 1.1.3 Vertebrate Eye Anatomy 1.1.4 Projection Areas of the Brain 1.2 Eye. Types of Eye Movement 1.2.1 Oculomotor Muscles and Field of View 1.2.2 Visual Acuity 1.2.3 Types of Eye Movement 1.2.4 Effects of Masking and Aftereffects 1.2.5 Perception of Contour and Contrast 1.2.6 Mach Bands, Hermann’s Grid 1.2.7 Light Contrast 1.2.8 Object Identification 1.2.9 Color Vision Abnormalities Subjective Color Sensations 1.3 Perception of Figures and Background 1.3.1 Dual Perception of the Connection “Figure-Background” 1.3.2 Gestalt Grouping Factors 1.3.3 Subjective Contours 1.3.4 The Dependence of Perception on the Orientation of the Figure 1.3.5 The Stroop Effect 1.4 Space Perception 1.4.1 Monocular Spatial Signs 1.4.2 Monocular Motion Parallax 1.4.3 Binocular Signs 1.4.4 Binocular Disparity and Stereopsis 1.5 Visual Illusions 1.5.1 Constancy Perception 1.5.2 The Development of the Process of Perception 1.5.3 Perception after Surgery Insight 1.5.4 Illusion of the Moon 1.5.5 Illusions of Muller-Lyer, Ponzo, Poggendorf, Zolner 1.5.6 Horizontal – Vertical Illusion 1.5.7 Illusions of Contrast 1.6 Conclusion References 2 Image Recognition Based on Compositional Schemes 2.1 Artistic Image 2.2 Classification of Features 2.3 Compositional Analysis of an Art Work 2.4 Classification by Shape, Position, Color 2.5 Classification According to the Content of the Scenes 2.6 Compositional Analysis in Iconography 2.7 Associative Mechanism of Analysis 2.8 Conclusions References 3 Sensory and Project Images in the Design Practice 3.1 Sensory Image Nature 3.2 Language and Images Symbolics 3.3 Methods of Images Production in Ideas 3.4 Personality Image Projecting 3.5 Project Image 3.6 Conclusion References 4 Associative Perception of Conceptual Models of Exhibition Spaces 4.1 Associative Modeling of the Exhibition Space Environment 4.1.1 Introduction 4.1.2 Conceptual and Terminological Apparatus of Conceptual Modeling and Shaping 4.1.3 Compositional and Planning Basis for Creating the Environment of Exhibition Spaces 4.1.4 Scenario Approach in the Figurative Solution of Environmental Spaces 4.1.5 Conceptual Approach to Creating Exhibition Spaces 4.1.6 Perception of the Figurative Solution of the Environment 4.2 Associative Modeling of Environmental Objects in Exhibition Spaces 4.2.1 Conceptual and Figurative Basis for the Formation of Environmental Objects 4.2.2 Associative and Imaginative Modeling of the Environmental Objects 4.2.3 Cognitive Bases of Perception of Associative-Figurative Models of Objects in Environmental Spaces 4.2.4 Perception of the Figurative Solution of an Environmental Object 4.2.5 Options of Conceptual and Figurative Modeling of Objects in Environmental Spaces 4.3 Conclusion References 5 Disentanglement For Discriminative Visual Recognition 5.1 Introduction 5.2 Problem Statement. Deep Metric Learning Based Disentanglement for FER 5.3 Adversarial Training Based Disentanglement 5.4 Methodology. Deep Metric Learning Based Disentanglement for FER 5.5 Adversarial Training Based Disentanglement 5.5.1 The Structure of Representations 5.5.2 Framework Architecture 5.5.3 Informative to Main-Recognition Task 5.5.4 Eliminating Semantic Variations 5.5.5 Eliminating Latent Variation 5.5.6 Complementary Constraint 5.6 Experiments and Analysis 5.6.1 Deep Metric Learning Based Disentanglement for FER 5.6.2 Adversarial Training-Based Disentanglement 5.7 Discussion 5.7.1 Independent Analysis 5.7.2 Equilibrium Condition 5.8 Conclusion References 6 Development of the Toolkit to Process the Internet Memes Meant for the Modeling, Analysis, Monitoring and Management of Social Processes 6.1 Introduction 6.2 Modeling of Internet Memes Distribution 6.3 Intellectualization of System for Processing the Internet Meme Data Flow 6.4 Implementation of Intellectual System for Recognition of Internet Meme Data Flow 6.5 Conclusion Acknowledgment References 7 The Use of the Mathematical Apparatus of Spatial Granulation in The Problems of Perception and Image Recognition 7.1 Introduction 7.2 The Image Processing and Analysis Base Conceptions 7.2.1 The Main Stages of Image Processing 7.2.2 The Fundamentals of a New Hybrid Approach to Image Processing 7.2.3 How is this New Approach Different? 7.3 Human Visual Perception Modeling 7.3.1 Perceptual Classification of Digital Images 7.3.2 The Vague Models of Digital Images 7.4 Mathematic Modeling of Different Kinds of Digital Images 7.4.1 Images as the Special Kind of Spatial Data 7.4.2 Fundamentals of Topology and Digital Topology 7.4.3 Regularity and the Digital Topology of Regular Regions 7.5 Zadeh’s Information Granulation Theory 7.6 Fundamentals of Spatial Granulation 7.6.1 Basic Ideas of Spatial Granulation 7.6.2 Abstract Vector Space 7.6.3 Abstract Affine Space 7.6.4 Cartesian Granules in an Affine Space 7.6.5 Granule-Based Measures in Affine Space 7.6.6 Fuzzy Spatial Relation Over the Granular Models 7.7 Entropy-Preserved Granulation of Spatial Data 7.8 Digital Images Granulation Algorithms 7.8.1 Matroids and Optimal Algorithms 7.8.2 Greedy Image Granulation Algorithms 7.9 Spatial Granulation Technique Applications 7.9.1 Granulation of Graphical DataBases 7.9.2 Automated Target Detection (ATD) Problem 7.9.3 Character Recognition Problem 7.9.4 Color Images Granulation in the Color Space 7.9.5 Spatial Granules Models for the Curvilinear Coordinates 7.9.6 Color Histogram for Color Images Segmentation 7.10 Conclusions References 8 Inverse Synthetic Aperture Radars: Geometry, Signal Models and Image Reconstruction Methods 8.1 Introduction 8.2 ISAR Geometry and Coordinate Transformations 8.2.1 3-D Geometry of ISAR Scenario 8.2.2 3-D to 2-D ISAR Geometry Transformation 8.3 2-D ISAR Signal Models and Reconstruction Algorithms 8.3.1 Linear Frequency Modulation Waveform 8.3.2 2-D LFM ISAR Signal Model Geometric Interpretation of Signal Formation 8.3.3 ISAR Image Reconstruction Algorithm 8.3.4 Correlation Spectral ISAR Image Reconstruction 8.3.5 Phase Correction Algorithm and Autofocusing 8.3.6 Barker Phase Code Modulation Waveform 8.3.7 Barker ISAR Image Reconstruction 8.3.8 Image Quality Criterion and Autofocusing 8.4 3-D ISAR Signal Models and Image Reconstruction Algorithms 8.4.1 Stepped Frequency Modulated ISAR Signal Model 8.4.2 ISAR Image Reconstruction Algorithm 8.4.3 Complementary Codes and Phase Code Modulated Pulse Waveforms 8.4.4 ISAR Complementary Phase Code Modulated Signal Modeling 8.4.5 ISAR Image Reconstruction Procedure 8.4.6 Parametric ISAR Image Reconstruction 8.5 Conclusions Acknowledgment References 9 Remote Sensing Imagery Spatial Resolution Enhancement 9.1 Introduction 9.2 Multiband Aerospace Imagery Informativeness 9.3 Equivalent Spatial Resolution of Multiband Aerospace Imagery 9.4 Multispectral Imagery Resolution Enhancement Based on Spectral Signatures’ Identification 9.5 Multispectral Imagery Resolution Enhancement Using Subpixels Values Reallocation According to Land Cover Classes’ Topology 9.6 Remote Sensing Longwave Infrared Data Spatial Resolution Enhancement 9.7 Issues of Objective Evaluation of Remote Sensing Imagery Actual Spatial Resolution 9.8 Conclusion References 10 The Theoretical and Technological Peculiarities of Aerospace Imagery Processing and Interpretation By Means of Artificial Neural Networks 10.1 Introduction 10.2 Peculiarities of Aerospace Imagery, Ways of its Digital Representation and Tasks Solved on It 10.2.1 Peculiarities of Technological Aerospace Imaging Process 10.2.2 Aerospace Imagery Defects 10.2.3 Aerospace Imagery Channel/Spectral Structure 10.2.4 Aerospace Imagery Spatial Resolution 10.2.5 Radiometric Resolution of Aerospace Imagery 10.2.6 Aerospace Imagery Data Volumes 10.2.7 Aerospace Imagery Labeling 10.2.8 Limited Availability of Aerospace Imagery 10.2.9 Semantic Features of Aerospace Imagery 10.2.10 The Tasks Solved by Means of Aerospace Imagery 10.2.11 Conclusion 10.3 Aerospace Imagery Preprocessing 10.3.1 Technological Stack of Aerospace Imagery Processing 10.3.2 Structuring and Accessing to Aerospace Datasets 10.3.3 Standardization of Measurements Representation 10.3.4 Handing of Random Channel/Spectral Image Structure 10.3.5 Ensuring of Image Sizes Necessary for Processing 10.3.6 Tile-Based Image Processing 10.3.7 Design of Training Samples from the Aerospace Imagery Sets 10.4 Interpretation of Aerospace Imagery by Means of Artificial Neural Networks 10.4.1 ANN Topologies Building Framework Used for Aerospace Imagery Processing 10.4.2 Object Non-Locality and Different Scales 10.4.3 Topology Customizing to the Different Channel/Spectral Structures of Aerospace Imagery 10.4.4 Integration of Aerospace Imagery with the Different Spatial Resolution 10.4.5 Instance Segmentation 10.4.6 Learning Rate Strategy 10.4.7 Program Interfaces Organization 10.4.8 Recommendations on the Framework Application 10.5 Conclusion References Index EULA