Computer and Robot Vision (Volume 1)

Cover......Page 1
Preface......Page 5
Contents......Page 8
1.1 Introduction......Page 16
1.2 Recognition Methodology......Page 20
1.2.2 Labeling......Page 21
1.2.5 Matching......Page 22
1.3 Outline of Book......Page 23
2.1 Introduction......Page 27
2.2 Thresholding......Page 28
2.2.1 Minimizing Within-Group Variance......Page 34
2.2.2 Minimizing Kullback information Distance......Page 37
2.3 Connected Components Labeling......Page 42
2.3.1 Connected Components Operators......Page 43
2.3.2 Connected Components Algorithms......Page 45
2.3.3 An Iterative Algorithm......Page 46
2.3.4 The Classical Algorithm......Page 48
2.3.5 A Space-Efficient Two-Pass Algorithm That Uses a Local Equivalence Table......Page 51
2.3.6 An Efficient Run-Length Implementation of the Local Table Method......Page 54
2.4 Signature Segmentation and Analysis......Page 62
2.5 Summary......Page 69
Exercises......Page 70
3.2 Region Properties......Page 73
3.2.1 Extremal Points......Page 76
3.2.2 Spatial Moments......Page 87
3.2.3 Mixed Spatial Gray Level Moments......Page 89
3.3 Signature Properties......Page 94
3.3.1 Using Signature Analysis to Determine the Center and Orientation of a Rectangle......Page 98
3.3.2 Using Signature Analysis to Determine the Center of a Circle......Page 102
Exercises......Page 105
4.1 Introduction......Page 109
4.2.1 Economic Gain Matrix......Page 110
4.2.2 Decision Rule Construction......Page 116
4.3 Prior Probability......Page 123
4.4 Economic Gain Matrix and the Decision Rule......Page 124
4.5 Maximin Decision Rule......Page 126
4.6 Decision Rule Error: Misidentification/False Identification......Page 140
4.7 Reserving Judgment......Page 143
4.9 A Binary Decision Tree Classifier......Page 145
4.9.1 Decision Tree Construction......Page 147
4.9.2 Decision Rules......Page 150
4.10 Decision Rule Error Estimation......Page 156
4.11 Neural Networks......Page 157
4.12 Summary......Page 158
Exercises......Page 160
5.1 Introduction......Page 170
5.2 Binary Morphology......Page 171
5.2.1 Binary Dilation......Page 172
5.2.2 Binary Erotion......Page 174
5.2.3 Hit-and-Miss Transform......Page 181
5.2.4 Dilation and Erosion Summary......Page 186
5.2.5 Opening and Closing......Page 187
5.2.7 Fast Dilations and Erosions......Page 202
5.3.1 Separation Relation......Page 204
5.3.2 Morphological Noise Cleaning and Connectivity......Page 208
5.3.4 Conditional Dilation......Page 209
5.4 Generalized Openings and Closings......Page 211
5.5 Gray Scale Morphology......Page 213
5.5.1 Gray Scale Dilation and Erosion......Page 214
5.5.2 Umbra Homomorphism Theorems......Page 218
5.5.3 Gray Scale Opening and Closing......Page 223
5.6 Openings, Closings, and Medians......Page 228
5.7 Bounding Second Derivatives......Page 231
5.8 Distance Transform and Recursive Morphology......Page 234
5.9 Generalized Distance Transform......Page 239
5.10 Medial Axis......Page 243
5.10.1 Medial Axis and Morphological Skeleton......Page 246
5.11 Morphological Sampling Theorem......Page 250
5.11.1 Set-Bounding Relationships......Page 254
5.11.2 Examples......Page 257
5.11.3 Distance Relationships......Page 261
5.12 Summary......Page 266
Exercises......Page 267
6.1 Introduction......Page 275
6.2.1 Region-Growing Operator......Page 281
6.2.2 Nearest Neighbor Sets and Influence Zones......Page 282
6.2.3 Region-Shrinking Operator......Page 283
Yokoi Connectivity Number......Page 284
Rutovitz Connectivity Number......Page 286
6.2.6 Connected Shrink Operator......Page 288
6.2.8 Thinning Operator......Page 290
6.2.9 Distance Transformation Operator......Page 291
6.2.11 Number of Shortest Paths......Page 294
6.3 Extremum-Related Neighborhood Operators......Page 295
6.3.1 Non-Minima-Maxima Operator......Page 296
6.3.2 Relative Extrema Operator......Page 297
6.3.3 Reachability Operator......Page 302
6.4.1 Convolution and Correlation......Page 303
6.4.2 Separability......Page 309
Exercises......Page 311
7.2 Noise Cleaning......Page 315
7.2.1 A Statistical Framework for Noise Removal......Page 317
7.2.3 Outlier or Peak Noise......Page 328
7.2.5 Gradient Inverse Weighted......Page 329
7.2.6 Order Statistic Neighborhood Operators......Page 330
7.2.7 A Decision Theoretic Approach to Estimating Mean......Page 333
7.2.8 Hysteresis Smoothing......Page 336
7.2.10 Selected-Neighborhood Averaging......Page 337
7.2.11 Minimum Mean Square Noise Smoothing......Page 339
7.2.12 Noise-Removal Techniques--Experiments......Page 341
7.3 Sharpening......Page 346
7.3.1 Extremum Sharpening......Page 348
7.4.1 Gradient Edge Detectors......Page 349
7.4.2 Zero-Crossing Edge Detectors......Page 358
7.4.3 Edge Operator Performance......Page 363
7.5 Line Detection......Page 364
Exercises......Page 366
Bibliography......Page 369
8.1 Introduction......Page 383
8.2 Relative Maxima......Page 384
8.3 Sloped Facet Parameter and Error Estimation......Page 387
8.4 Facet-Based Peak Noise Removal......Page 390
8.5 Iterated Facet Model......Page 392
8.6 Gradient-Based Facet Edge Detection......Page 394
8.7 Bayesian Approach to Gradient Edge Detection......Page 403
8.8 Zero-Crossing Edge Detector......Page 404
8.8.1 Discrete Orthogonal Polynomials......Page 405
8.8.3 Equal-Weighted Least-Squares Fitting Problem......Page 406
8.9 Integrated Directional Derivative Gradient Operator......Page 415
8.9.1 Integrated Directional Derivative......Page 416
8.9.2 Experimental Results......Page 417
8.10 Corner Detection......Page 422
8.10.1 Incremental Change along the Tangent Line......Page 424
8.10.3 Instantaneous Rate of Change......Page 425
Facet Model - Based Corner Detectors......Page 427
Comparison with Other Gray Tone Corner Detectors......Page 428
8.11 Isotropic Derivative Magnitudes......Page 431
8.12 Ridges and Ravlnes on Digital Images......Page 436
8.12.1 Directional Derivatives......Page 437
8.12.2 Ridge-Ravine Labeling......Page 438
Invariance Requirement......Page 442
8.13.2 Mathematical Classification of Topographic Structures......Page 443
Pit......Page 445
Ridge......Page 446
Flat......Page 447
Hillside......Page 448
Summary of the Topographic Categories......Page 449
Invariance of the Topographic Categories......Page 450
Ridge and Ravine Continua......Page 451
8.13.3 Topographic Classification Algorithm......Page 452
Case Two: One Zero Crossing......Page 453
Case Three: Two Zero Crossings......Page 454
8.13.4 Summary of Topographic Classification Scheme......Page 455
Previous Work......Page 456
Exercises......Page 457
Bibliography......Page 461
9.1 Introduction......Page 465
9.2 Gray Level Co-Occurrence......Page 469
9.3 Strong Texture Measures and Generalized Co-Occurrence......Page 474
9.3.1 Spatial Relationships......Page 475
9.4 Autocorrelation Function and Texture......Page 476
9.5 Digital Transform Methods and Texture......Page 477
9.6 Textural Energy......Page 479
9.7 Textural Edgeness......Page 481
9.8 Vector Dispersion......Page 482
9.9 Relative Extrema Density......Page 483
9.10 Mathematical Morphology......Page 485
9.11 Autoregression Models......Page 487
9.12 Discrete Markov Random Fields......Page 489
9.13 Random Mosaic Models......Page 492
9.15 Texture Segmentation......Page 493
9.16 Synthetic Texture Image Generation......Page 494
9.17 Shape from Texture......Page 495
Exercise......Page 505
Bibliography......Page 506
10.1 Introduction......Page 520
10.2 Measurement-Space-Guided Spatial Clustering......Page 522
10.2.1 Thresholding......Page 531
10.2.2 Multidimensional Measurement-Space Clustering......Page 535
10.3.1 Single-Linkage Region Growing......Page 536
10.3.2 Hybrid-Linkage Region Growing......Page 537
10.3.3 Centroid-Linkage Region Growing......Page 543
10.4 Hybrid-Linkage Combinations......Page 547
10.5 Spatial Clustering......Page 548
10.6 Split and Merge......Page 551
10.7 Rule-Based Segmentation......Page 553
10.8 Motion-Based Segmentaion......Page 556
10.9 Summary......Page 559
Exercises......Page 560
Bibliography......Page 561
11.1 Introduction......Page 565
11.2.2 Border-Tracking Algorithm......Page 566
11.3 Linking One-Pixel-Wide Edges or Lines......Page 568
11.4 Edge and Line Linking Using Directional Information......Page 571
11.5 Segmentation of Arcs into Simple Segments......Page 572
11.5.1 Iterative Endpoint Fit and Split......Page 573
11.5.2 Tangential Angle Deflection......Page 575
11.5.3 Uniform Bounded-Error Approximation......Page 579
11.5.4 Breakpoint Optimization......Page 581
11.5.5 Split and Merge......Page 583
11.5.6 Isodata Segmentation......Page 584
11.5.7 Curvature......Page 585
Finding Straight-Line Segments......Page 588
Finding Circles......Page 592
Variations......Page 594
11.6.2 A Bayesian Approach to the Hough Transform......Page 595
11.7 Line Fitting......Page 598
11.7.1 Variance of the Fitted Parameters......Page 601
11.7.2 Principal-Axis Curve Fit......Page 605
11.8 Region-of-Support Determination......Page 607
11.9 Robust Line Fitting......Page 609
11.10 Least-Squares Curve Fitting......Page 612
11.10.1 Gradient Descent......Page 615
11.10.3 Second-Order Approximation to Curve Fitting......Page 617
11.10.4 Fitting to a Circle......Page 618
11.10.5 Variance of the Fitted Parameters......Page 627
11.10.6 Fitting to a Conic......Page 631
11.10.7 Fitting to an Ellipse......Page 632
11.10.8 Bayesian Fitting......Page 634
11.10.9 Uniform Error Estimation......Page 635
Exercises......Page 637
Bibliography......Page 641
Appendix A......Page 649
Appendix B......Page 669
Appendix C Experimental Protocol......Page 676
Index......Page 678