Proceedings of 3rd International Conference on Computer Vision and Image Processing: CVIP 2018, Volume 1

Preface......Page 6
Contents......Page 8
About the Editors......Page 12
 1 Introduction......Page 14
 3 Proposed Method......Page 16
  3.2 Detecting Salient Regions......Page 17
  3.3 Representation Extraction Using Deep CNNs......Page 18
  3.4 Training Using Multi-class SVM......Page 19
  4.2 Experimental Scenarios......Page 20
 5 Conclusion......Page 22
 References......Page 23
 1 Introduction......Page 24
 2 Related Work......Page 26
  3.1 Saliency-Based Feature Extraction......Page 27
  3.2 Using Deep CNNs for Extracting Features......Page 28
  4.1 Description of Dataset......Page 29
 5 Experimental Results......Page 30
 6 Conclusions......Page 31
 References......Page 32
 1 Introduction......Page 34
  1.1 Related Work......Page 35
  2.2 Segmentation of Lungs Region and Preprocessing......Page 36
  2.3 Feature Extraction......Page 38
 3 Experimentation and Performance Evaluation......Page 39
 4 Results and Discussions......Page 41
 5 Conclusion and Future Work......Page 44
 References......Page 45
 1 Introduction......Page 47
 2 Generalized Autocalibrating Partially Parallel Acquisition (GRAPPA)......Page 48
  2.1 Optimum Parameter Selection Strategies for Regularization......Page 50
 3 Results......Page 52
 5 Conclusion......Page 56
 References......Page 57
Improving Image Quality and Convergence Rate of Perona–Malik Diffusion Based Compressed Sensing MR Image Reconstruction by Gradient Correction......Page 58
 2 Related Work......Page 59
 3 Theory......Page 60
 4 Method......Page 62
  4.3 Datasets Used......Page 63
 5 Results and Discussion......Page 64
  5.1 Computational and Time Complexity......Page 66
 6 Conclusion......Page 67
 References......Page 68
 1 Introduction and Formulation......Page 70
 2 Blind Quality Assessment of PFA-Affected Images......Page 72
 3 Proposed Chromatic Eigenvalue Ratio-Based Quality Measure......Page 74
 4 Results and Discussions......Page 76
 5 Conclusions......Page 80
 References......Page 81
Investigation on the Muzzle of a Pig  as a Biometric for Breed Identification......Page 82
 1 Introduction......Page 83
 2 Problem Statement: MUZZLE for Breed Analysis of Pigs......Page 84
 3 Gradient Profiling and Patch Statistics......Page 85
 4 Diversity in Patch Statistics Across Breeds......Page 87
 5 Testing and Inferencing Procedure......Page 92
 6 Conclusion......Page 93
 References......Page 94
 1 Introduction......Page 95
  2.1 Prior Art......Page 96
  3.1 Finding Representative Data......Page 97
  4.1 Sparsity-Inducing Norm for Multi-block-Natured Data......Page 98
  4.2 Selection of Representatives......Page 99
  5.2 Results......Page 100
  5.3 Computational Time Comparison......Page 101
 References......Page 102
 1 Introduction......Page 104
 2 Related Work......Page 105
 3 Pattern Formulation......Page 106
 4 Pattern Selection......Page 107
  4.1 Single Pattern Matching......Page 108
  4.2 Multi-pattern Matching......Page 109
 5 Evaluation Criterion......Page 111
 6 Experiments, Results, and Discussion......Page 112
 7 Conclusion......Page 114
 References......Page 115
 1 Introduction......Page 117
  2.1 Data Acquisition......Page 118
  2.3 GRAPPA Reconstruction......Page 119
  2.4 Methods for Coil Combination......Page 121
 3 Results......Page 122
 4 Discussion......Page 124
 References......Page 125
 1 Introduction......Page 127
 2 Down Syndrome......Page 128
 3 Related Work......Page 130
 4 Proposed Architecture......Page 131
  4.1 Preprocessing and Region Extraction......Page 132
  4.2 Deep CNN’s for Extracting Representations......Page 133
  4.3 Classification Using Support Vector Machines......Page 134
  5.2 Experimental Scenarios......Page 135
 6 Conclusion......Page 137
 References......Page 138
 1 Introduction......Page 139
 2 Related Works and Contributions......Page 141
  3.1 GIST Features......Page 142
  3.3 Kernel Weighted Collaborative Representation Classification (KWCRC)......Page 143
  4.1 Spectral Ocular Database......Page 146
  4.3 Protocol 1—Same Session Evaluation......Page 147
  4.4 Protocol 2—Cross-Session Evaluation......Page 148
 5 Conclusions......Page 149
 References......Page 150
 1 Introduction......Page 152
 2 Proposed Architecture......Page 154
  2.1 Specular Feature Extraction......Page 155
  2.3 Learning the Conditional Densities......Page 156
 3 Performance Evaluation......Page 160
 4 Conclusions......Page 161
 References......Page 162
 1 Introduction......Page 163
  2.1 Generation of Sparse Map......Page 165
  2.2 Generation of Dense Map......Page 169
 3 Experimental Results and Discussion......Page 172
 References......Page 173
 1 Introduction......Page 175
 2 Related Works......Page 177
 3 Feature Generation......Page 178
  3.1 Extraction of Low-Level Stroke (LLS) Features......Page 179
  3.2 Feature Vector Generation......Page 181
  4.2 Classifier......Page 182
  4.3 Experimental Results......Page 183
 References......Page 186
 1 Introduction......Page 188
 2 Review......Page 189
 3 Architecture of the Integrated Semi-Supervised Learning and Classification Model......Page 190
  3.1 Supervised Convolutional AIS: Module 1......Page 192
  3.2 Enhancement of the model with misclassification error: module 2......Page 193
  3.3 Semi-Supervised Convolution-AIS: Module 3......Page 195
 4 Experiments and Results......Page 196
 5 Discussions and Conclusions......Page 198
 References......Page 199
 1 Introduction......Page 201
 2 The Proposed Method......Page 202
 3 Experimental Results and Discussion......Page 206
 References......Page 209
 1 Introduction......Page 211
 2 Related Work......Page 212
  3.1 Face Frontalization......Page 214
  3.2 ell1,1-Sparse-ELM Based Domain Adaptation (ell1,1-Sparse-EDA)......Page 216
  3.3 PIFR-EDA......Page 219
  4.1 Datasets and Experimental Setup......Page 220
  4.2 Experimental Results and Observations......Page 221
 5 Conclusion......Page 222
 References......Page 223
 1 Introduction......Page 225
  2.1 Marking Region of Interest (ROI)......Page 226
  2.2 Long-Term and Short-Term Model for Background Subtraction......Page 227
  2.4 Back-Tracing to Find Owner......Page 229
 3 Datasets......Page 232
 4 Results and Experiments......Page 233
 References......Page 235
 1 Introduction......Page 237
 2 Compressed Representation and Related Terminologies......Page 239
 3 Model Building......Page 241
  3.1 Top-Down/Bottom-Up Approach: Entropy Computation......Page 242
  3.2 Hypothesis for the Top-Down Approach: An Example......Page 243
  3.3 Column-Wise Approach: Entropy Computation......Page 244
 4 Illustration......Page 245
  4.1 An Example......Page 246
 5 Discussion and Conclusion......Page 247
 References......Page 248
 1 Introduction......Page 250
  1.2 Computer-Aided Diagnosis for Prostate Cancer......Page 251
 2 Method......Page 252
 3 Results......Page 254
 5 Conclusion......Page 255
 References......Page 256
Detecting Face Morphing Attacks with Collaborative Representation  of Steerable Features......Page 258
 1 Introduction......Page 259
 2 Proposed Method......Page 261
 3 Experiments and Results......Page 264
 4 Conclusion......Page 266
 References......Page 267
Vehicle Speed Determination and License Plate Localization from Monocular Video Streams......Page 269
 1 Introduction......Page 270
  2.3 License Plate Localization......Page 271
  3.1 Vehicle Detection......Page 272
  3.2 Vehicle Tracking......Page 273
  3.3 Vehicle Speed Estimation......Page 275
  3.4 License Plate Localization......Page 276
 References......Page 278
 1 Introduction......Page 280
 2 Methodology......Page 283
  2.3 Expanding Path......Page 284
  3.1 Weighted Multi-class Logistic Loss......Page 285
  3.2 Dice Loss......Page 287
  4.2 Data Preprocessing......Page 288
  5.1 Qualitative Analysis......Page 289
  5.2 Quantitative Metrics......Page 290
 6 Conclusion......Page 291
 References......Page 292
 1 Introduction......Page 294
 2 Recent Works......Page 296
 3 Methodology......Page 297
  3.1 Objectness Prior......Page 299
  3.2 Fusion of Priors......Page 300
  4.2 Results: Visual Comparison......Page 301
  4.3 Results: Computation Time and Quantitative Performance Analysis......Page 303
 5 Conclusion......Page 305
 References......Page 306
 1 Introduction......Page 308
  1.1 Proposed Techniques and Approaches for Image Segmentation......Page 309
  1.2 Experiments and Results......Page 310
  1.3 Discussions and Conclusion......Page 311
 References......Page 312
Eigenvector Orientation Corrected LeNet for Digit Recognition......Page 314
 2 Related Works......Page 315
  2.4 Spatial Transformer Network......Page 316
 3 Proposed Method: Eigenvector Orientation Correction for Rotated Digits......Page 317
  4.2 Orientation Correction for Rotated Digits......Page 319
  4.3 EOCL on Rotated MNIST and MNIST_rot_12k Test Datasets......Page 321
  4.4 Comparing Performance of EOCL with Other Approaches......Page 324
 References......Page 325
 1 Introduction......Page 326
  2.1 Log-Polar Mapping......Page 328
  2.2 All Phase Biorthogonal Sine Transform......Page 329
  3.1 Watermark Generation Process......Page 331
 4 Experimental Results......Page 332
 5 Conclusion......Page 337
 References......Page 338
 1 Introduction......Page 339
 2 Theoretical Background......Page 342
  3.1 Reformulation of the Problem......Page 343
  3.2 Optimal Solution......Page 344
 4 Experiments and Results......Page 345
 5 Discussions......Page 347
 6 Conclusion......Page 349
 References......Page 350
 1 Introduction......Page 352
 3 Video Sequences......Page 354
  3.2 Sequence 2......Page 355
  3.6 Sequence 6......Page 356
 4 Ground Truth and Organization of Dataset......Page 357
  4.2 Ground Statistics of the Dataset......Page 358
 References......Page 361
Recent Advancements in Image-Based Prediction Models for Diagnosis of Plant Diseases......Page 364
 1 Introduction......Page 365
 2 Remote Sensing and Imaging Techniques......Page 366
  3.1 RGB Imaging......Page 368
  3.2 Hyperspectral Imaging......Page 371
  3.3 Other Imaging Techniques......Page 372
 References......Page 375
 1 Introduction......Page 377
 2 Mathematical Formulation of LRCF......Page 380
  2.1 Design Algorithm of LRCF......Page 381
  3.2 Performance of LRCF......Page 382
 4 Conclusion......Page 387
 References......Page 388
Storm Tracking Using Geostationary Lightning Observation Videos......Page 389
 2 Literature Survey......Page 390
  3.2 Proposed Clustering Algorithm......Page 391
  3.3 Preprocessing of Videos and Tracking Without Prediction......Page 392
  3.4 Tracking with Prediction......Page 393
  3.5 Disaster Predictors from Video Data......Page 394
 4 Results......Page 395
 5 Conclusions......Page 399
 References......Page 400
Human Head Pose and Eye State Based Driver Distraction Monitoring System......Page 401
 1 Introduction......Page 402
 2 Literature Survey......Page 403
  4.1 Introduction......Page 405
  4.2 Face Detection......Page 406
  4.3 Eye Region Extraction......Page 407
  4.4 Drowsiness......Page 408
  4.5 Inattentiveness......Page 411
 5 Experimental Result......Page 412
 7 Future Scope......Page 417
 References......Page 419
 1 Introduction......Page 420
 2 Proposed Palmprint Recognition System......Page 422
  2.1 Block-Wise ULBP Histogram (BULBPH) as Descriptor......Page 423
  2.2 KDA for Dimension Reduction and Enhanced Discrimination......Page 424
 3 Experimental Results and Discussions......Page 426
  3.1 Comparison of Dimension Reduction Techniques  on BULBPH......Page 429
 4 Comparison with the Related Works......Page 430
 References......Page 431
 1 Introduction......Page 433
 2 Related Work......Page 434
 3 The Portable Object (PO) Dataset......Page 436
  4.1 The Office Dataset......Page 437
  4.2 Data Preprocessing and Feature Extraction......Page 438
  4.3 Domain Adaptation......Page 439
  4.4 GAN Based Domain Adaptation......Page 440
 5 Performance Analysis......Page 442
 References......Page 443
A Deep Learning Framework Approach for Urban Area Classification Using Remote Sensing Data......Page 445
 1 Introduction......Page 446
  3.1 Support Vector Machine (SVM)......Page 447
 4 Proposed Approach (PA)......Page 448
 5 Results and Discussion......Page 450
 References......Page 451
Image-Based Facial Expression Recognition Using Local Neighborhood Difference Binary Pattern......Page 453
 1 Introduction......Page 454
 2 Proposed Methodology......Page 455
  2.2 Facial Feature Extraction and Dimensionality Reduction......Page 456
 3 Experimental Results and Discussion......Page 459
  3.2 Parameter Selection......Page 460
  3.3 Results on CK+ Dataset......Page 463
  3.4 Results on RFD Dataset......Page 464
 4 Conclusion......Page 465
 References......Page 466
Author Index......Page 467