This book applies novel theories to improve algorithms in complex data analysis in various fields, including object detection, remote sensing, data transmission, data fusion, gesture recognition, and medical image processing and analysis.
It is intended for Ph.D. students, academics, researchers, and software developers working in the areas of digital video processing and computer vision technologies.
Author(s): Margarita N. Favorskaya; Lakhmi C. Jain
Publisher: Springer International Publishing
Year: 2020
Language: English
Commentary: True EPUB
Pages: 321
Table of contents :
Preface......Page 6
Contents......Page 7
About the Editors......Page 13
1.1 Introduction......Page 15
1.2 Chapters Including in the Book......Page 16
References......Page 20
Technical Applications......Page 22
Abstract......Page 23
2.1 Introduction......Page 24
2.2 Mathematical Models of Images......Page 25
2.3 Representation and Processing of One-Dimensional Autoregressions with Multiple Roots of Characteristic Equations......Page 33
2.4 Representation and Processing of Multidimensional Random Fields Generated by Autoregressions with Multiple Roots of Characteristic Equations......Page 46
2.5 Real Image Processing......Page 56
2.6 Conclusions......Page 59
References......Page 61
Abstract......Page 65
3.1 Introduction......Page 66
3.2.1 Doubly Stochastic Models of Random Fields......Page 68
3.2.2 Analysis of Double Stochastic Models......Page 69
3.2.3 Estimation of Parameters of Double Stochastic Models......Page 70
3.3.1 Synthesis of Double Stochastic Filter......Page 73
3.3.2 Analysis of Double Stochastic Filter......Page 74
3.3.3 Block Double Stochastic Filter......Page 77
3.3.4 Double Stochastic Filter for Multispectral Image Processing......Page 80
3.3.5 Restoration of Multispectral Images Based on Double Stochastic Filtering......Page 84
3.4 Detection of Objects Against the Background of Multispectral Satellite Images......Page 85
3.4.1 Synthesis of Object Detection Algorithms......Page 86
3.4.2 Analysis of Object Detection Algorithms......Page 88
3.5.1 Thematic Mapping of Satellite Images......Page 92
3.5.2 Monitoring of Natural Objects......Page 93
3.6 Autoregressive Models of Images on a Circle......Page 99
3.6.1 Models of Random Fields on a Cylinder......Page 100
3.6.2 Models of Random Fields on a Circle......Page 101
3.6.3 Doubly Stochastic Models of Random Fields on a Circle......Page 103
3.6.4 Filtration and Identification......Page 105
3.7 Conclusions......Page 107
References......Page 108
Abstract......Page 110
4.2 Direct and Inverse Problems in the Communication Theory......Page 111
4.3 Least Squares Method and Pseudo-Inverse Matrix......Page 114
4.4 Singular-Value Decomposition and Moore-Penrose Matrix......Page 115
4.5 Singular Regularization......Page 117
4.6 Levenberg–Marquardt Algorithm for Non-linear Equations Solution......Page 118
4.7 Iteration Algorithms for Inverse Problems Solution......Page 119
4.8 Solution of Convolutional Integral Equation and Wiener’s Filtering......Page 121
4.9 Elimination of Images Spreading in Multimedia Communication Links......Page 122
4.10 Inverse Problem of Source Localization......Page 123
4.11 Inverse Problem of Micro-Strip Sensors Reconstruction......Page 124
4.12 Inverse Problem for Signal Analysis......Page 126
References......Page 128
Abstract......Page 130
5.1 Introduction......Page 131
5.2 Overview of Transmitting Specifications and Possible Attacks......Page 132
5.2.1 Transmitting Specifications......Page 133
5.2.2 Possible Attacks......Page 138
5.3 Related Work......Page 140
5.4 Selecting Relevant Regions in Semi I-Frames......Page 145
5.4.1 Motion Map......Page 146
5.4.2 Saliency Map......Page 148
5.4.3 Textural Map......Page 150
5.4.5 Joint Map......Page 154
5.5.1 Scale-Invariant Feature Points Extraction......Page 156
5.5.2 Exponential Moments......Page 157
5.5.3 Embedding Scheme......Page 159
5.5.4 Extraction Scheme......Page 160
5.6 Experimental Studies......Page 165
References......Page 167
Abstract......Page 172
6.1 Introduction......Page 173
6.2 Related Work......Page 177
6.3 Methodology......Page 179
6.4.2 Object Selection and Adaptive Thresholding......Page 185
6.4.3 Adaptive Thresholding Based on Invariant Geometric Criteria......Page 190
6.5 Applications......Page 196
6.6 Conclusions......Page 201
Acknowledgements......Page 202
References......Page 203
Medical Applications......Page 206
Abstract......Page 207
7.1 Introduction......Page 208
7.2 Related Work......Page 209
7.3.1 Region of Interest Detection......Page 213
7.3.2 Feature Extraction......Page 216
7.4 Russian Sign Language Database......Page 218
7.5 Technical Characteristics of the Collected Database......Page 220
7.6 Proposed Framework and Evaluation Experiments......Page 221
7.7 Conclusions......Page 228
References......Page 229
8.1 Introduction......Page 234
8.2 Related Work......Page 238
8.3 Methods of Endoscopic Images Enhancement......Page 241
8.3.1 Methods and Algorithms for Noise Reduction in Medical Endoscopic Images......Page 242
8.3.2 Methods and Algorithms for Endoscopic Images Contrast and Brightness Enhancement......Page 249
8.4 Method of Endoscopic Images Visualization (Virtual Chromoendoscopy)......Page 252
8.5.1 Two-Stage Method for Polyp Detection and Segmentation......Page 255
8.5.2 Block-Based Algorithm for Bleeding Detection......Page 262
8.6 Conclusions......Page 270
References......Page 271
Abstract......Page 274
9.1 Introduction......Page 275
9.2 Related Work......Page 276
9.3 Medical Experiment Description......Page 277
9.4 The Proposed Method of Medical Images Analysis......Page 280
9.4.1 Noise Reduction......Page 281
9.4.2 Brightness Correction with Contrast Enhancement......Page 283
9.4.3 Formation of Contour Representation......Page 284
9.4.4 Color Coding of Objects......Page 287
9.5 Experimental Research......Page 288
9.5.1 Description of Experimental Medical Data......Page 289
9.5.2 Evaluation of Brightness Parameters of Medical Images......Page 290
9.5.3 Evaluation of Medical Characteristics......Page 294
9.6 Conclusion......Page 299
References......Page 300
Abstract......Page 304
10.1 Introduction......Page 305
10.2 Related Work......Page 306
10.3 The Histological Image Dataset......Page 309
10.4 The Development of Automatic Histological Image Segmentation Algorithms......Page 310
10.4.1 Histological Image Segmentation Algorithm Based on AlexNet Neural Network......Page 311
10.4.2 Fast Histological Image Segmentation Algorithm Based on U-Net Neural Network......Page 314
10.5 Morphological Filter......Page 316
10.6.1 Comparison of the Segmentation Results for Histological Images at the Output of Algorithm 1 and Algorithm 2......Page 318
10.6.2 The Use of Morphological Filtration as a Means of Additional Processing......Page 322
10.7 Conclusions......Page 324
References......Page 325
Author Index......Page 329
