دانلود کتاب Applications of hybrid metaheuristic algorithms for image processing

فهرست مطالب :

Preface......Page 6
Contents......Page 8
Hybrid Metaheuristics and€Image Segmentation......Page 11
Segmentation of€Thermal Images Using Metaheuristic Algorithms for€Failure Detection on€Electronic Systems......Page 12
1 Introduction......Page 13
2 Thermography......Page 14
3.1 Otsu Variance......Page 15
3.2 Kapur Entropy......Page 16
4 Optimization Algorithms......Page 17
5.1 Thermal Image Segmentation Interface......Page 19
5.2 Software Processing......Page 20
6 Experimental Result......Page 22
Appendix......Page 34
References......Page 35
1 Introduction......Page 36
2 Remote Sensing Data......Page 38
3.1 Corner Detection for Image Registration......Page 39
3.2 Endmember Extraction and Unmixing Pixels......Page 43
3.3 Segmentation and Classification......Page 47
4 Discussion......Page 57
References......Page 59
Hybrid Grey-Wolf Optimizer Based Fractional Order Optimal Filtering for€Texture Aware Quality Enhancement for€Remotely Sensed Images......Page 61
1 Introduction......Page 62
2 Cuckoo Search Algorithm Based Hybridization of€Grey Wolf Optimization......Page 65
3 Fractional-Order Adaptive Image Sharpening......Page 69
4 Proposed Texture Dependent Optimal Fractional-Order Adaptive Filtering Based Augmented Framework......Page 72
5.1 Assessment Criterion......Page 78
5.2 Qualitative Assessments......Page 82
5.3 Quantitative Assessments......Page 83
6 Conclusion......Page 84
References......Page 85
Robust K-Means Technique for€Band Reduction of€Hyperspectral Image Segmentation......Page 88
2 Related Work......Page 89
3.1 K-Means Clustering Method......Page 90
3.4 Particle Swarm Optimization (PSO)......Page 91
3.5 Determining the€Number of€Clusters......Page 92
4 Proposed Method......Page 94
4.1 Band Reduction Using ROBUST K-MEANS Algorithm......Page 96
4.2 Algorithm of€Enhanced Estimation of€Centroid (EEOC)......Page 97
5 Experimental Result......Page 99
5.1 Result Analysis......Page 100
References......Page 107
Ethnic Characterization in Amalgamated People for Airport Security Using a Repository of Images and Pigeon-Inspired Optimization (PIO) Algorithm for the Improvement of Their Results......Page 111
1 Introduction......Page 112
2 Pigeon-Inspired Optimization Algorithm......Page 113
3 Multiple Matching......Page 117
4 Multivariable Analysis......Page 118
5 Experimentation......Page 121
6 Conclusions and Future Research......Page 123
References......Page 125
1 Introduction......Page 126
2 Preliminaries......Page 129
2.2 Particle Swarm Optimization......Page 130
2.3 Sine–Cosine Algorithm......Page 132
3 Image Thresholding Segmentation Method......Page 134
3.1 Generate the€Non-local Means 2D Histogram......Page 135
3.3 Objective Function: Rényi Entropy......Page 136
3.4 The 2DNLMeKGSA Method......Page 138
4 Experimental Results......Page 139
4.1 Performance Evaluation Parameters......Page 141
4.2 Experimental Analyses......Page 145
5 Conclusion......Page 151
References......Page 153
Hybrid Metaheuristics and€Other Image Processing Tasks......Page 155
1 Introduction......Page 156
2 Template Matching Process......Page 158
4 The General Procedure Followed by€TM Algorithms Based on€Metaheuristic Optimization Methods......Page 161
5 Experimental Results......Page 162
6 Conclusions......Page 166
Appendix......Page 167
References......Page 168
1 Introduction......Page 170
2 General Shape Retrieval Framework......Page 172
2.1 Shape Characterization Using Laws of Texture Energy Measures......Page 173
2.2 Shape Characterization Using Hexagonal Grid-Based Triangular Tessellation (HGTT)......Page 174
2.3 Shape Description by Blending Phase Congruency and Histogram of Oriented Gradients......Page 178
3.1 MPEG-7 CE Shape-1 Part B Dataset......Page 183
3.2 Tari-1000 Dataset......Page 185
3.3 Kimia's 99 Dataset......Page 186
References......Page 187
Clustering Data Using Techniques of€Image Processing Erode and€Dilate to€Avoid the€Use of€Euclidean Distance......Page 189
1 Introduction......Page 190
2.1 Data Representation......Page 191
2.2 Operation of€Dilatation and€Erosion......Page 192
2.3 K-means......Page 194
3 Metric to€Validate the€Comparison of€Clusters......Page 195
4 The Approach of€Images Techniques to€Clustering......Page 196
5 Experimental Results......Page 198
References......Page 204
1 Introduction......Page 206
2 Stitching......Page 208
2.2 Image Registration......Page 209
2.3 Alignment......Page 211
3 Homography......Page 213
4 Evolutionary Algorithms......Page 217
5 Artificial Bee Colony ABC......Page 220
6.2 Second Program to€Do Stitching Step by€Step with€Evolutionary Algorithm......Page 223
6.3 Tests......Page 225
7 Conclusions......Page 229
References......Page 230
Active Contour Model in Deep Learning Era: A Revise and Review......Page 232
1 Introduction......Page 233
2.1 Active Contour—Background......Page 234
2.2 Implicit Active Contour—Level Set......Page 235
2.3 LS-Based Image Segmentation......Page 237
2.4 State-of-the-Art AC Methods......Page 239
3.1 Multi-Layer Neural Network......Page 241
3.2 Convolutional Neural Networks......Page 243
3.3 Recurrent Neural Networks......Page 246
4.1 Active Contour as Post-processing......Page 248
4.2 Active Contour Is Used Within DL as End-to-End Framework......Page 250
4.3 Active Contour in the Loss Function......Page 254
References......Page 255
Linear Regression Techniques for€Car Accident Prediction......Page 262
1 Introduction......Page 263
2.2 Estimated Straight Line......Page 264
2.4 Least Square Method......Page 267
3 Developing a€Predictive Model Using MATLAB......Page 269
4 Evolutionary Techniques......Page 272
4.1 Gradient Descent......Page 273
4.2 Particle Swarm Optimization......Page 276
4.3 Differential Evolution......Page 278
4.4 Artificial Bee Colony......Page 280
5 Results......Page 282
6 Conclusions......Page 283
References......Page 284
1 Introduction......Page 286
2.1 Inspiration Analysis......Page 288
2.2 Mathematical Model for Salp Chains......Page 290
3.1 Hybridization......Page 291
3.2 Improved SSA......Page 294
3.3 Variants of SSA......Page 298
4 Applications of SSA in Optimization Problems......Page 302
5 Discussion......Page 303
6 Conclusion......Page 304
References......Page 305
Health Applications......Page 310
Segmentation of€Magnetic Resonance Brain Images Through the€Self-Adaptive Differential Evolution Algorithm and€the€Minimum Cross-Entropy Criterion......Page 311
1 Introduction......Page 312
2.1 Minimum Cross-Entropy......Page 314
2.2 Multilevel Thresholding......Page 315
3 Self-Adaptive Differential Evolution......Page 316
3.1 Differential Evolution......Page 317
3.2 SADE Algorithm......Page 319
4.1 Solution Representation......Page 322
4.3 Multilevel Thresholding......Page 323
5 Experimental Results......Page 324
5.1 Standard Test Images......Page 326
5.2 MR Brain Images......Page 332
6.1 Statistical Analysis Standard Test Images......Page 338
7 Conclusions......Page 344
References......Page 347
Automatic Detection of Malignant Masses in Digital Mammograms Based on a MCET-HHO Approach......Page 351
1 Introduction......Page 352
2 Image Segmentation......Page 355
2.1 Minimum Cross Entropy Method......Page 356
3 Harris Hawks Optimization......Page 357
4.1 Datasets Description......Page 360
4.2 Preprocessing......Page 361
4.3 MCET-HHO Segmentation......Page 364
4.5 Validation......Page 365
5 Results and Discussion......Page 366
6 Conclusions......Page 371
References......Page 372
1 Introduction......Page 375
2.1 Machine Learning......Page 377
2.2 Optimization and€Evolutionary Techniques......Page 380
3 Problem Formulation......Page 388
3.1 Pre-process of€Data......Page 390
3.3 Artificial Neural Network Process......Page 391
4 Results......Page 392
References......Page 396
1 Introduction......Page 399
2.2 Clinical Image Processing......Page 401
3.2 Feature Extraction......Page 403
3.3 RMDL......Page 405
3.4 Prediction......Page 406
4 Experiments and€Results......Page 407
References......Page 410
Fuzzy-Crow Search Optimization for€Medical Image Segmentation......Page 412
1 Introduction......Page 413
2.1 Data Acquisition......Page 414
2.3 Fuzzy C Means Clustering......Page 415
2.4 Crow Search Optimization......Page 416
2.5 FCM-Crow Optimization Segmentation Algorithm......Page 419
2.6 Tuning of€Parameters for€Optimization Algorithms......Page 420
3 Results and€Discussion......Page 421
4 Hardware Implementation......Page 427
5 Conclusion......Page 435
References......Page 436
Intelligent System for the Visual Support of Caloric Intake of Food in Inhabitants of a Smart City Using a Deep Learning Model......Page 439
2 Proposal Methodology......Page 440
2.2 Considerations of Our Problems and Their Impact on Society......Page 442
2.3 Food Recognition Module......Page 445
3.1 Experimentation......Page 447
4.1 Results of the Segmentation Network......Page 449
5 Multivariable Analysis......Page 450
6 Conclusions and Future Research......Page 451
References......Page 452
1 Introduction......Page 454
2 Kapur’s Entropy for Multilevel Thresholding......Page 456
4 Cuckoo Search Optimization Algorithm......Page 457
4.1 Explanation of€CS Algorithm......Page 459
5 Results......Page 460
5.1 Peak Signal-To-Noise Ratio (PSNR) and€Structural Similarity Index (SSIM) Metrics......Page 462
6 Conclusions......Page 467
References......Page 468
1.1 The Anatomy of the Eye......Page 469
2.1 Introduction to the Generative Models......Page 471
2.2 Parameter Estimation......Page 473
3.1 Generative Adversarial Networks (GANs)......Page 475
3.2 Steps for Designing Generative Adversarial Network......Page 477
3.3 Generative Adversarial Networks Application......Page 479
4 Synthetic Retinal Image Generation......Page 481
5 Conclusion......Page 483
References......Page 484