Foreword xv
About the Authors xvii
Preface xix
Acknowledgments xxi
Acronyms xxiii
About the Companion Website xxv
Part I Fundamentals 1
1 Introduction 3
1.1 Electromagnetic Spectrum and Visible Band 4
1.2 Types of Images 5
1.3 Applications of Image Processing 10
1.4 Image Processing Methods and Organization of the Book 18
1.5 Chapter Summary 22
2 Human Visual System and Image Perception 23
2.1 History 23
2.2 Human Visual System: Eye–Brain Channel 25
2.3 A Conceptual Model for Human Visual Systems 30
2.4 Vision Theories 31
2.5 Characteristics of Human Visual System 36
2.6 Chapter Summary 41
3 Mathematical Tools for Image Processing 43
3.1 Image Representation 43
3.2 A Simple Image Formation Model 47
3.3 Discrete Geometry 48
3.4 Adjacency, Path, and Connectivity 53
3.5 Object(s), Background, Edges, and Boundaries 55
3.6 Sampling and Quantization 56
3.7 Image Interpolation 61
3.8 Mathematical Operations for Image Processing 66
3.9 Chapter Summary 76
4 Color Representation 77
4.1 Color Generation from the Electromagnetic Spectrum 78
4.2 Trichromatic Theory for Color Sensation 80
4.3 Mathematical Representation of Color 81
4.4 Color Normalization and Chromaticity Diagrams 94
4.5 Color Histograms 95
4.6 Measuring Image Similarity by Histograms 100
4.7 Pseudocoloring 103
4.8 Color Quantization 106
4.9 Face Detection from Skin Color 107
4.10 Chapter Summary 109
Part II Low-level Image Processing Methods 111
5 Spatial Image Enhancement by Point Operations 113
5.1 Color Transforms 114
5.2 Histogram Processing 120
5.3 Chapter Summary 133
6 Spatial Image Enhancement by Filtering: Convolution 135
6.1 Spatial Filtering: Gathering Information from Pixel Groups 135
6.2 2D Convolution and Correlation Operations 137
6.3 Practical Implementation of Convolution for Image Processing 138
6.4 How Does Convolution Work as a Filter? 140
6.5 2D Convolution as a Spatial Filter 142
6.6 Smoothing Filters 143
6.7 Gaussian Filters 146
6.8 Median Filters 147
6.9 Sharpening Filters: Edge Detectors 149
6.10 Chapter Summary 170
7 Image Transforms 171
7.1 Vector Spaces for Images 172
7.2 Matrix Algebra for Image Processing 174
7.3 Fourier Transform of Images 180
7.4 Fourier Transform of 2D Discrete Functions, Formulated as a Matrix Transform 184
7.5 Discrete Cosine Transform 190
7.6 Hadamard Transform 194
7.7 Filtering in Transform Domain 197
7.8 Transform Domain Filters 199
7.9 Chapter Summary 210
8 Wavelet Transforms and Multiresolution Image Analysis 213
8.1 Wavelet Transforms 215
8.2 Image Pyramids and Trees 233
8.3 Sub-band Coding 239
8.4 Chapter Summary 250
Part III Intermediate-level Image Processing Methods 253
9 Image Compression 255
9.1 Data and Information 256
9.2 Measuring Information 259
9.3 Entropy: Average Information 262
9.4 Information Content of Image 265
9.5 Source Coding Theorem 266
9.6 Compression Ratio and Relevant Redundancy 267
9.7 Types of Redundancies in Images 268
9.8 Objective Measures for Image Fidelity 276
9.9 Image Compression Methods 278
9.10 An Image Compression Model as an Information Channel 278
9.11 Algorithms for Reducing the Redundancies in Source Encoder 280
9.12 Image File Formats 298
9.13 Chapter Summary 299
10 Morphological Image Processing 301
10.1 Mathematical Morphology 302
10.2 Morphological Operations for Binary Images 306
10.3 Image Processing Techniques with Binary Morphological Operations 316
10.4 Applying Binary Morphology for Color Images 324
10.5 Intensity-based Morphology for Color Images 327
10.6 Image Processing Techniques Using Intensity-based Morphological Operations 332
10.7 Popular Applications of Morphological Operations in Image Processing 340
10.8 Chapter Summary 340
11 Image Segmentation 341
11.1 Types of Segmentation Algorithms 341
11.2 Formal Definition of Image Segmentation 343
11.3 Region Growing, Split-and-Merge Algorithms 346
11.4 Statistical Clustering Algorithms 350
11.5 Deterministic Clustering Methods: Spectral Clustering 371
11.6 Segmentation by Boundary Extraction 386
11.7 Consensus Segmentation 400
11.8 Chapter Summary 402
12 Image Representation by Feature Extraction 403
12.1 Region Representation by Shape Features 404
12.2 Region Representation with Color and Texture Features 425
12.3 Co-occurrence Matrix 429
12.4 Texture Descriptors Based on Co-occurrence Matrix 431
12.5 Gabor Filters 433
12.6 Scale Invariant Feature Transform 434
12.7 Local Binary Patterns 442
12.8 Whole Image Representation 445
12.9 Chapter Summary 450
Part IV High-level Image Processing Methods by Deep Neural Networks 451
13 Artificial Neural Networks: A Brief Overview 453
13.1 What Is Natural Learning? 454
13.2 What Is Artificial Learning? 455
13.3 Types of the Learning Problem 457
13.4 Types of Learning Algorithms 459
13.5 Model Estimation by Artificial Neural Networks 467
13.6 Inference Algorithm 479
13.7 Fundamental Assumptions of Neural Network Algorithms 479
13.8 Experimental Setup for Measuring the Performance 482
13.9 Performance Measures 483
13.10 Overfitting and Underfitting Problem 489
13.11 Chapter Summary 494
14 Key Deep Learning Architectures for Image Processing Tasks 495
14.1 Convolutional Neural Networks 495
14.2 Autoencoders 504
14.3 Variational Autoencoders 512
14.4 Generative Adversarial Networks 519
14.5 Diffusion Models 524
14.6 Vision Transformers 529
14.7 Comparison of Key Deep Learning Architectures for Image Processing 537
14.8 Transfer Learning 538
14.9 Chapter Summary 541
15 Deep Learning Approaches to Image Processing Tasks 543
15.1 Image Denoising 544
15.2 Image Super-resolution 545
15.3 Image Colorization 546
15.4 Image Inpainting 549
15.5 Image Compression and Dimensionality Reduction 550
15.6 Image Segmentation 552
15.7 Image-to-Image Translation 553
15.8 Text-to-Image Generation 555
15.9 Image-to-Text Generation 557
15.10 Style Transfer 558
15.11 Object Detection 558
15.12 Challenges and Limitations of Deep Learning Methods in Image Processing 561
15.13 Chapter Summary 563
Bibliography 565
Index 575
