دانلود کتاب Image and video technology, 9 conf., PSIVT 2019, Sydney

فهرست مطالب :

Preface......Page 6
Organization......Page 8
Contents......Page 12
A Fused Pattern Recognition Model to Detect Glaucoma Using Retinal Nerve Fiber Layer Thickness Measurements......Page 15
1 Introduction......Page 16
2.1 Data Set......Page 17
2.2 Statistical Data Analysis......Page 19
3.1 Overview......Page 20
3.4 Validation of Our Study......Page 22
4 Results......Page 24
References......Page 25
1 Introduction......Page 27
2 Methodology......Page 29
2.1 Pre-processing of the Input Facial Image......Page 30
2.2 Feature Extraction Using the Proposed Feature Descriptor......Page 31
2.3 Face Recognition Using 2D-Hiden Markov Model (2DHMM)......Page 32
3 Results......Page 33
4 Discussion......Page 34
References......Page 39
1 Introduction......Page 41
2 Related Work......Page 42
3.1 Fish Observation......Page 43
4.1 Object Detection......Page 44
4.2 Semantic Segmentation......Page 45
5.1 Visual Assessment......Page 46
5.3 Objective Motion Analysis......Page 47
6 Experimental Results......Page 49
7 Conclusion and Future Work......Page 52
References......Page 53
1 Introduction......Page 55
2 Related Works......Page 56
3.1 System Architecture......Page 57
3.2 Soft Attention Mask and Data Augmentation......Page 59
4 Experiments and Results......Page 60
References......Page 64
1 Introduction......Page 66
2 Related Works......Page 68
3.1 Backbone Network......Page 71
3.2 BackNet Architecture......Page 72
4.2 Experimental Setup......Page 73
4.3 Quantitative Results Analysis......Page 74
5 Conclusions......Page 75
References......Page 76
1 Introduction......Page 79
2 Related Work......Page 81
3 Methodology......Page 82
6 Results......Page 88
7 Conclusion......Page 89
References......Page 90
1 Introduction......Page 92
2.1 Data......Page 95
2.2 Data Pre-processing......Page 96
2.4 Analysis......Page 99
3 Results......Page 100
4 Conclusion and Discussions......Page 103
References......Page 104
1 Introduction......Page 106
2 Experimental Setup......Page 107
3.1 Age Detection......Page 109
3.2 Defect Detection......Page 112
References......Page 117
1 Introduction......Page 120
2 The Discrete Cosine Basis for Motion......Page 122
3.1 Discrete Cosines Basis Oriented Prediction Generation......Page 123
3.2 Discrete Cosine Based Motion Compensated Prediction as a Reference Frame......Page 125
4 Experimental Analysis......Page 126
References......Page 127
1 Introduction......Page 130
2.2 Double Channel 3D Convolutional Neural Network Model (D3DCNN)......Page 132
2.5 Double Channel Spatial-Temporal Feature Fusion Algorithms......Page 134
3.1 Experimental Dataset and Experimental Settings......Page 136
3.3 Analysis of Experimental Results of EMV-1 Dataset......Page 137
References......Page 140
1 Introduction......Page 142
2 Proposed Method......Page 145
2.1 Generating and Embedding Watermarked Data......Page 146
2.2 Tamper Detection and Localization......Page 148
2.3 Recovery of Tampered Blocks......Page 149
2.4 Recovery of Tampered Image......Page 150
3 Experimental Results......Page 151
References......Page 154
1 Introduction......Page 156
2 Methodology......Page 158
2.2 Proposed Depth Augmented Networks for Fine-Tuning......Page 159
3.1 Datasets and Implementation Details......Page 160
3.3 Layers to Be Frozen for Optimal Performance......Page 161
3.4 Performance Analysis of Proposed Depth Augmented Networks......Page 162
3.5 Average Performance Gain......Page 166
References......Page 167
1 Introduction......Page 170
2 Related Work......Page 171
2.2 Horse Physiology and Pain Estimation......Page 172
3.2 Manual Measurement Description......Page 173
4.2 Mask Generation for Horse Candidate Extraction......Page 174
4.3 Extracting Horse Orientation and Viewing Direction......Page 175
4.4 Tracking and Motion Parameters......Page 176
5.2 Interpreting Horses\' Motion in Relation to Stress or Pain......Page 177
6 Summary and Discussion......Page 181
References......Page 182
1 Introduction......Page 184
2.1 Motivation......Page 186
2.2 Pseudo Image Generation......Page 188
2.3 Weight Computation for Fusion......Page 189
2.4 Multi-scale Image Fusion......Page 190
3 Experimental Result......Page 191
4 Conclusion......Page 195
References......Page 196
Abstract......Page 198
1 Introduction......Page 199
2 Proposed Grapevine Nutritional Disorder Detection Technique......Page 200
2.1 Development of Nutrient Deficiency/Toxicity Symptoms......Page 201
2.2 Machine Learning and Image Analysis......Page 202
3 Experimental Results......Page 206
4 Conclusion......Page 208
References......Page 209
1 Introduction......Page 211
2.1 Cuboid Segmentation......Page 214
2.2 Merging......Page 216
3.2 Performance Evaluation......Page 218
4 Conclusion......Page 222
References......Page 223
High-Resolution Realistic Image Synthesis from Text Using Iterative Generative Adversarial Network......Page 225
1 Introduction and Related Work......Page 226
2.1 Common Techniques......Page 228
2.2 The 1st Iteration Details......Page 230
2.3 The 2nd Iteration Details......Page 231
3 Experiments......Page 232
3.2 Results of iGAN All Iterations......Page 233
3.3 Comparisons......Page 234
References......Page 237
1 Introduction......Page 239
2 Related Work......Page 241
3.1 Overview......Page 242
3.2 Non-rigid Registration of the SMPL Model......Page 243
3.3 Sparse Representation of Human Shape Deformation......Page 245
3.4 Shape Deformation Bases and Coefficients Estimation by Neural Network......Page 246
4 Experiment......Page 247
4.2 Inter-frame Interpolation......Page 248
4.3 Intra-frame Interpolation......Page 250
References......Page 251
1 Introduction......Page 254
2 Related Work......Page 256
3 Saliency Feature......Page 257
4 Our Approach......Page 258
4.1 DCF Overview......Page 260
4.2 Tracker Robustness Measurement......Page 261
5 Experimentation and Analysis......Page 262
References......Page 266
1 Introduction......Page 269
2 COCO Trained Model for Quick Inference......Page 271
4 Perspective Transformation......Page 273
6 Real World Coordinates......Page 275
6.1 Ellipse Fitting and Minor Diameter Measurement......Page 276
6.2 Box Width Measurement......Page 279
7 Conclusion......Page 280
References......Page 282
1 Introduction......Page 283
2 Prior Work......Page 286
3 The Proposed Deep Image Registration Framework......Page 287
4 Experimental Results and Discussion......Page 289
References......Page 292
1 Introduction......Page 295
2 Related Work......Page 296
3 Multimodal 3D Facade Reconstruction......Page 297
3.2 Dense RGB-D Data Generation......Page 298
4 Evaluations......Page 302
4.1 Evaluation of the Segmentation of the Facade Elements Made of Glass in Images......Page 303
4.2 Evaluation of Facade Mesh Models......Page 304
5 Comparison Study......Page 305
6 Conclusion......Page 306
References......Page 307
1 Introduction......Page 310
1.1 Organization......Page 312
2.1 Sparse Preserve Projection......Page 313
3.1 The Construction of MSPP......Page 314
3.2 Optimization of MSPP......Page 316
4.1 Datasets......Page 317
4.2 Experiments on Datasets......Page 318
References......Page 321
1 Introduction......Page 324
2 Motivation and Proposed Objective Function......Page 325
3.1 An Equivalent Formulation......Page 328
3.2 Solution Algorithm......Page 329
3.3 Proof of Convergence......Page 331
4 Experimental Results......Page 335
5 Conclusion......Page 337
References......Page 338
1 Introduction......Page 339
2.2 Feature Selection......Page 341
2.3 Prostate Cancer Classification......Page 343
3 Result and Performance Comparisons......Page 344
References......Page 349
1 Introduction......Page 351
2.1 Gray Value Image and Convolution Filter......Page 353
3.1 Our Approach......Page 356
4 Experiments......Page 359
4.1 Results......Page 360
5 Summary and Conclusion......Page 362
References......Page 363
1 Introduction......Page 365
3 Algorithm......Page 368
3.2 Radar Feature Descriptor......Page 369
3.3 RVNet Architecture......Page 370
3.4 RVNet Variants......Page 372
4 Experimental Section......Page 374
References......Page 377
1 Introduction......Page 379
2 Related Work......Page 380
3.1 Data Collection......Page 381
3.3 Dataset Comparison......Page 382
4.2 Convolutional LSTM......Page 384
4.4 Spatial-Temporal Inference......Page 385
5.1 Performance Index......Page 386
5.3 Results and Comparisons......Page 388
References......Page 391
1 Introduction......Page 393
2.1 The Discriminative Network......Page 395
2.2 The Generative Network......Page 396
3.1 The Metric for Shoeprints Segmentation......Page 399
3.2 Ablation Study......Page 400
3.3 Comparisons with Other End-to-End Methods......Page 401
References......Page 402
1 Introduction......Page 404
2.1 Deep Features......Page 405
2.2 Handcrafted Features......Page 406
3 Proposed Method......Page 407
3.1 Object Detection and Tracking......Page 408
3.2 Position Checking......Page 410
4.1 Experimental Environment......Page 411
4.2 Results and Discussion......Page 413
5 Conclusion and Future Work......Page 415
References......Page 416
1 Introduction......Page 418
2 Related Works......Page 420
3.1 Initial Deep Features Extraction......Page 421
3.2 K-Means Clustering over Deep Features......Page 422
3.3 Unsupervised Deep Features Encoding......Page 423
4.2 Experimental Setup......Page 424
4.4 Analysis of Results......Page 425
5 Conclusion......Page 427
References......Page 428
Author Index......Page 430