Proc. 4 inter. conf. Computer Vision and Image Processing, CVIP 2019, Part 1

Preface......Page 6
Organization......Page 7
Contents – Part I......Page 9
Contents – Part II......Page 13
Biometrics......Page 18
 1 Introduction......Page 19
  2.1 Statistical Features......Page 21
  2.2 Transform-Based Features......Page 22
 3 Experimental Setup and Results......Page 23
  3.1 Results of Statistical Feature Descriptor......Page 24
  3.2 Results of Transform-Based Feature Descriptor......Page 26
 References......Page 27
Computer Forensic......Page 29
 1 Introduction......Page 30
  2.2 Finding Keypoints and Extraction of Features Using SIFT......Page 32
  2.4 Feature Matching......Page 33
  3.1 Dataset Description......Page 34
  3.2 Metrics for Performance Evaluation......Page 35
  3.4 Qualitative Results......Page 36
 References......Page 39
Computer Vision......Page 40
 1 Introduction......Page 41
  2.1 Use of Computer Vision in Fault Detection in the Pipe Industry......Page 42
 3 Problem Definition......Page 43
  4.1 Comparing the State-of-the-Art Circle Detection Algorithms......Page 44
  4.2 Preprocessing......Page 45
  4.3 Morphological Processing: Intensification of Foreground......Page 46
  4.6 Region-Based Hough Transform......Page 47
 5 Results......Page 48
 6 Discussion and Future Work......Page 50
 References......Page 51
 1 Introduction......Page 53
 2 Related Work......Page 54
  3.1 Multi-camera Image Fusion......Page 55
  3.2 Multi Camera Video Transition......Page 59
 4 Experimental Results......Page 60
 5 Conclusion......Page 63
 References......Page 64
 1 Introduction......Page 65
 2 Proposed Algorithm......Page 67
 3 Simulation Results......Page 68
  3.2 Evaluation Parameters......Page 69
 References......Page 73
 1 Introduction......Page 75
 2 Related Work......Page 76
  3.1 Model Architecture......Page 77
  3.2 Loss Function......Page 79
 4 Experimental Analysis......Page 81
 References......Page 85
 1 Introduction......Page 87
  1.1 Overview of Laplacian Pyramid Blending......Page 88
  2.1 Proposed Spatially Variant Level-Based Blending......Page 90
  3.1 Qualitative Comparisons......Page 93
  3.2 Quantitative Comparisons......Page 94
 References......Page 95
 1 Introduction......Page 96
 2 Related Work......Page 97
 3 Proposed System......Page 98
  3.2 Spatial Transformer Network......Page 99
  3.3 Convolutional Neural Network......Page 100
  3.4 GPU Embedded Development Board......Page 101
 4 Implementation and€Results......Page 102
 References......Page 106
 1 Introduction......Page 108
 2 Related Works......Page 110
 3 Proposed Methods for Depth Estimation......Page 112
  3.3 Method 3: Models Using Weight Matrix Pruning......Page 113
 4 Experiments and Results......Page 114
 5 Conclusion......Page 117
 References......Page 118
Dimension Reduction......Page 120
 1 Introduction......Page 121
 2 Problem Statement......Page 123
  3.2 Redundancy......Page 124
 4 Proposed Feature Selection Framework......Page 125
  5.3 Experiment Architecture......Page 127
  5.4 Comparative Study......Page 128
 6 Conclusion......Page 129
 References......Page 130
Healthcare Information Systems......Page 132
 1 Introduction......Page 133
  2.2 Feature Extraction......Page 135
  2.3 Feature Selection......Page 136
 3 Classification......Page 137
  3.2 Convolutional Neural Network......Page 138
 4 Experimental Results and Discussions......Page 139
 References......Page 141
 1 Introduction......Page 144
 3 Proposed Method......Page 146
  3.1 Problem Formulation......Page 147
  4.1 Noiseless Case......Page 150
  4.2 Noisy Case......Page 153
 5 Conclusion......Page 154
 References......Page 155
 1 Introduction......Page 156
 2 Related Works......Page 157
  3.2 Damage Patterns......Page 158
  3.3 DataSet......Page 159
 4 Computational Model Architecture......Page 160
  5.1 Phase 1......Page 161
  5.2 Phase 2......Page 163
  5.3 Phase 3......Page 164
  5.4 Phase 4......Page 165
 References......Page 166
 1 Introduction......Page 168
 2 Literature Survey......Page 169
 3 Proposed Method......Page 170
  3.3 Gamma Adjustment......Page 171
  3.5 Feature Extraction......Page 172
  3.6 Artificial Neural Network......Page 174
  3.7 Support Vector Machine (SVM)......Page 175
 References......Page 182
 1 Introduction......Page 184
  2.1 Encoder-Decoder Framework......Page 186
  2.2 Context Level Visual Attention (CLVA)......Page 187
  2.3 Textual Attention (TA)......Page 188
  3.1 Training Algorithm......Page 189
  3.2 Quantitative and Qualitative Results......Page 190
 4 Conclusion......Page 191
 References......Page 192
Image Processing......Page 193
 1 Introduction......Page 194
 2 Wavelet Shrinkage......Page 196
 3 Proposed Methodology......Page 197
  4.1 Qualitative Analysis......Page 199
  4.2 Quantitative Analysis......Page 200
 References......Page 202
 1 Introduction......Page 204
 2 Cellular Automaton Model......Page 206
  3.1 Multithreshold Binary Conversion (MBC)......Page 207
  3.2 Recombination of Binary Images (RBI)......Page 208
 4 Experimental Result......Page 210
 References......Page 212
 1 Introduction......Page 214
 2 Proposed Algorithm......Page 215
  2.1 Entity Detection......Page 216
  2.2 Entity Correlation......Page 219
 3 Results......Page 221
 4 Applications......Page 223
 References......Page 224
 1 Introduction......Page 225
  2.1 Denoising......Page 227
  2.4 Uniform Deblurring......Page 228
  2.5 Merging......Page 230
 3 Implementation and Results......Page 231
 References......Page 234
 1 Introduction......Page 236
  1.1 Motivation......Page 237
 2 State-of-the-Art......Page 238
 3 Recapture Video Dataset......Page 239
 4 Proposed Methodology......Page 241
 5 Experimental Result......Page 244
 References......Page 246
 1 Introduction......Page 248
 2 Related Work......Page 249
 3 Methodology......Page 250
 4 Results and Analysis......Page 252
 References......Page 255
 1 Introduction......Page 257
 2 Defocus Model......Page 258
 3 Proposed Depth Map Estimation......Page 259
  4.1 Range......Page 261
  4.2 Ground Truth......Page 264
 5 Verification......Page 265
 6 Conclusion......Page 266
 References......Page 267
Image Segmentation......Page 268
 1 Introduction......Page 269
 2 Background......Page 270
  3.1 Optical Flow......Page 271
 4 Proposed Framework......Page 272
  4.2 Lung Nodule Segmentation......Page 273
 5 Experimental Results......Page 274
 References......Page 276
 1 Introduction......Page 278
 2 Proposed Method......Page 279
  2.1 Warping Position Parameters......Page 281
  2.2 Warping Control Parameters......Page 282
  2.3 Calculating the Warping Factors......Page 283
 3 Experimental Results and Evaluation......Page 284
 References......Page 286
 1 Introduction......Page 289
  2.1 Point Set Simplification......Page 291
 3 Results and€Discussions......Page 293
  3.2 Reconstruction Broken Alphabet......Page 294
  3.3 Reconstruction Dot-Matrix Alphabet......Page 295
 4 Conclusion......Page 296
 References......Page 297
 1 Introduction......Page 299
 2 Graph Cut in Image Segmentation......Page 300
 3 Reduced Graph Cut with Flexible User Input......Page 301
 4 Experimental Results and Comparison......Page 304
  4.1 User Study......Page 305
  4.2 Comparison with Other State-of-the-art Methods......Page 306
 References......Page 308
 1 Introduction......Page 309
 2 Fuzzy Clustering Algorithm by Incorporating Constrained Class Uncertainty-Based Entropy......Page 311
  3.1 Experiments on BrainWeb Data......Page 313
  3.2 Experiments on Clinical Brain MR Image Data......Page 315
 4 Conclusion......Page 316
 References......Page 317
 1 Motivation......Page 319
 2 Related Work......Page 320
 3 Proposed System Framework......Page 322
  3.3 Cascade Encoder-Decoder Network......Page 323
 4 Training of Proposed OBJECTNet......Page 324
  5.1 Performance on Videos of CDnet-2014......Page 325
  5.3 Computational Complexity Analysis......Page 327
 References......Page 328
 1 Introduction......Page 331
  2.1 Images and€Graphs......Page 332
  2.2 Construction of€Forest......Page 333
  2.3 Proposed Segmentation Process......Page 334
 3 Results and€Discussions......Page 335
 4 Conclusion......Page 339
 References......Page 340
 1 Introduction......Page 342
 2 Related Work......Page 343
 3 Feature Extraction......Page 344
  3.2 Directional Distance Distribution......Page 345
  3.3 Gabor......Page 346
  3.4 DCT......Page 347
  3.5 Zernike Moments......Page 348
 4 Classification Methods......Page 349
  4.2 k-Nearest Neighbor (k-NN)......Page 350
 5 Performance Evaluation......Page 352
 References......Page 353
 1 Introduction......Page 356
 2 Quaternion......Page 357
 3 Modified Gray-Centered RGB Colour Cube......Page 359
 4 Linear Quaternion Convolution (LQC)......Page 361
 6 Results and€Discussion......Page 362
 7 Conclusion......Page 365
 References......Page 366
Information Retrieval......Page 367
 1 Introduction......Page 368
 2 Retrieval of Documents......Page 369
  2.1 Non-text Based Document Retrieval......Page 370
  2.2 Text Based Document Retrieval......Page 372
  2.3 Combined Query Formation and Retrieval......Page 374
 3 Experimental Results......Page 375
 References......Page 377
 1 Introduction......Page 379
  2.2 Local Ternary Co-occurrence Pattern (LTCoP)......Page 381
  3.1 Directional Structure Transformed Pattern......Page 382
  3.2 Proposed Transformed Directional Tri Concomitant Triplet Patterns (TdtCTp)......Page 383
  3.3 Proposed System Framework......Page 384
  4.1 Retrieval Accuracy on Corel Dataset......Page 385
  4.2 Retrieval Accuracy on VIA/I-ELCAP Dataset......Page 386
 5 Conclusion......Page 387
 References......Page 388
 1 Introduction......Page 390
 2 Related Work......Page 391
 4 Conventional Approach......Page 392
 5 Proposed Method......Page 393
 7 Training......Page 395
 8 Results and€Inferences......Page 397
 References......Page 400
  1.1 Motivation......Page 402
  1.2 Related Work......Page 403
  2.1 Residual Learning......Page 405
  2.2 Index Matching and Image Retrieval......Page 406
  3.1 Retrieval Accuracy on Corel-10K Dataset......Page 407
  3.2 Retrieval Accuracy on GHIM-10K Dataset......Page 408
 References......Page 409
Instance Based Learning......Page 412
 1 Introduction......Page 413
 2 Related Work......Page 415
 3 Proposed Method......Page 416
  3.1 BlobBag......Page 417
  3.2 SpiderBag......Page 419
 4 Evaluation......Page 420
 References......Page 422
Machine Learning......Page 425
 1 Introduction......Page 426
 2 Related Work......Page 427
  3.1 Dataset Description of Big Mart......Page 428
  3.3 Data Cleaning......Page 429
  3.5 Model Building......Page 430
 4 Implementation and Results......Page 433
 5 Conclusions......Page 435
 References......Page 436
Author Index......Page 438