1. 1 motivation 1
1.2 Why is computer vision difficult 2
1.3 image expression and image analysis task 4
1.4 Summary 7
1.5 Reference 7
Chapter II Images, Their Expression and Properties 8
2. 1 Expressed some concepts vividly 8
Continuous image function 8
2.2 image digitization 10
2.2. 1 sampling 10
2.2.2 Quantization 1 1
2.3 digital image properties 12
2.3. 1 digital image metric sum
Topological attribute 12
Histogram 16
2.3.3 Entropy 17
2.3.4 Visual perception of images 18
Image quality 20
2.3.6 Noise in the image
2.4 Color Images 22
2.4. 1 color physics 22
2.4.2 Color perceived by people 23
2.4.3 Color Space 26
Palette image 28
2.4.5 Color constancy 28
2.5 Camera Overview 29
2.5. 1 photosensitive sensor 29
2.5.2 Black and white camera 30
2.5.3 Color camera 32
2.6 Summary 33
2.7 References 34
Chapter 3 Images and Their Mathematical and Physical Background 35
3. 1 overview 35
3. 1. 1 linear 35
3. 1.2 Dirac distribution sum
Convolution 35
3.2 Integral Linear Transformation 37
3.2. 1 as an image of the linear system 37
3.2.2 Introduction to Integral Linear Transformation 37
3.2.3 1D Fourier transform 38
3.2.4 2D Fourier Transform 4 1
3.2.5 Sampling and Shannon Limit 43
Discrete Cosine Transform 46
Wavelet transform 47
Feature analysis 5 1
Singular value decomposition 52
3.2. 10 principal component analysis 53
3. 2. 1 1 other orthogonal image transformations 54
3.3 Image as a Random Process 55
3.4 Physics of image formation 57
3.4. 1 as the image of radiation measurement 57
3.4.2 Image Acquisition and Geometrical Optics 57
3.4.3 Lens Aberration and Radial Distortion 60
3.4.4 Image acquisition from the perspective of radiology 62
Surface reflection 64
3.5 Summary 67
3.6 References 67
Chapter 4 Data Structure of Image Analysis 69
4. 1 hierarchy of image data representation 69
4.2 Traditional image data structure 70
4.2. 1 matrix 70
Chain 72
Topological data structure 73
Relationship structure 73
4.3 Hierarchical Data Structure 74
4.3. 1 Pyramid 74
Quadtree 75
4.3.3 Other pyramid structures 76
4.4 Summary 77
4.5 References 78
The fifth chapter image preprocessing 79
5. 1 pixel brightness transformation 79
5. 1. 1 position-related brightness correction 80
5. 1.2 gray scale transformation 80
5.2 Geometric transformation 82
5.2. 1 pixel coordinate transformation 83
5.2.2 Brightness Interpolation 84
5.3 Local Pretreatment 86
Image smoothing 86
5.3.2 Edge detection operator 92
5.3.3 Zero crossing of second derivative 96
5.3.4 Proportion in image processing 98
5.3.5 Canny Edge Extraction 100
Parametric edge model 102
5.3.7 Edge in Multispectral Images 103
5.3.8 Frequency domain local preprocessing 103
5.3.9 Using local preprocessing operators
Line detection 108
5.3. 10 corner (point of interest) detection 109
5. 3. 1 1 maximum stability limit area detection 1 12
5.4 Image Restoration 1 14
5.4. 1 easily recoverable degeneration 1 14
5.4.2 Inverse filtering 1 15
Wiener filter 1 15
5.5 Summary 1 17
5.6 Reference 1 18
The first part of chapter 6 124
6. 1 threshold 124
6. 1. 1 threshold detection method 126
6. 1.2 optimal threshold 127
6. 1.3 Multispectral Threshold 129
6.2 Edge-based segmentation 130
6.2. 1 threshold of edge image 13 1
6.2.2 Edge Relaxation Method 133
Boundary tracking 135
6.2.4 Edge Tracking as Graphic Search 139
6.2.5 Edge Tracking as Dynamic Programming 146
6.2.6 Hough transform 149
6.2.7 Using boundary position information
Boundary detection 155
6.2.8 Construction of 156 area from the border.
6.3 Region-based Segmentation 157
6.3. 1 The area was merged into 158.
6.3.2 Regional Division 160
6.3.3 Split and merge 16 1
6.3.4 watershed division 163
6.3.5 Post-processing of regional growth 166
6.4 Matching 166
6.4. 1 matching standard 167
6.4.2 Matching control strategy 168
6.5 Evaluation of Sub-paragraph 169
6.5. 1 supervision and evaluation 169
6.5.2 Unsupervised Assessment 172
6.6 Summary 172
6.7 Reference 175
Chapter 7, Part 2 182
7. 1 mean shift segmentation 182
7.2 Active Contour Model -Snake 187
7.2. 1 classic snakes and balloons 188
7.2.2 Extension 19 1
7.2.3 gradient vector flow snake 19 1
7.3 Geometric Deformation Model-Level Set Sum
Geodetic active contour 194
7.4 Fuzzy Connectivity 200
7.5 Face to 3D Image Segmentation 204
7.5. 1 simultaneous detection of boundary pairs 205
7.5.2 Excellent surface inspection 208
7.6 graph cut segmentation 209
7.7 Optimal Single and Multi-surface Segmentation 2 14
7.8 Summary 223
7.9 References 224
Chapter 8 Shape Representation and Description 232
8. 1 region ID 234
8.2 Shape representation and description based on contour 236
8.2. 1 chain code 237
8.2.2 Simple Geometric Boundary Representation 237
8.2.3 Boundary Fourier Transform 239
8.2.4 Use the boundary description of fragment sequence 24 1
B-spline representation 243
8.2.6 Other contour-based shapes
Describe method 245
8.2.7 Shape unchanged 245
8.3 Based on the shape representation and description of region 248
8.3. 1 Simple Scalar Region Description 248
8.3.2 Torque 25 1
Convex shell 253
8.3.4 Graphical representation based on regional skeleton 257
Domain decomposition 259
8.3.6 This area is adjacent to Figure 260.
8.4 Shape Category 26 1
8.5 Summary 26 1
8.6 References 263
Chapter 9 Object Identification 270
9. 1 knowledge representation 270
9.2 Statistical Pattern Recognition 274
9.2. 1 classification principle 275
Classifier settings 276
Classifier learning 278
9.2.4 Support Vector Machine 280
9.2.5 Cluster analysis 284
9.3 Neural Network 286
9.3. 1 feedforward network 287
9.3.2 Unsupervised Learning 288
9.3.3 Hopfield neural network 289
9.4 Syntactic Pattern Recognition 290
Grammar and Language 29 1
Grammar analysis and grammar classifier 293
9.4.3 Syntactic classification learning and
Grammar derivation 294
9.5 Recognition as Pattern Matching 295
Isomorphism of graphs and subgraphs 296
9.5.2 Similarity of charts 298
9.6 Optimization Technology in Identification 299
9.6. 1 genetic algorithm 300
Simulated annealing 302
9.7 Fuzzy System 303
9.7. 1 fuzzy set and fuzzy membership function 304
9.7.2 Fuzzy Set Operation 305
Fuzzy reasoning 306
9.7.4 Fuzzy System Design and Training 308
9.8 Enhancement Method in Pattern Recognition 309
9.9 Summary 3 1 1
9 9. 10/0Reference 3 14
Chapter 10 Image Understanding 3 19
10. 1 image understanding control strategy 320
10. 1. 1 parallel and serial processing control 320
10. 1.2 hierarchical control 32 1
10. 1.3 bottom-up control 32 1
Model-based control 32 1
10. 1.5 hybrid control strategy 322
10. 1.6 Non-hierarchical control 325
10.2 RANSAC: consistent by random sampling.
Suitable for 326
10.3 point distribution model 329
10.4 activity apparent model 337
10.5 Pattern Recognition Method in Image Comprehension 344
10.5. 1 classification-based segmentation 344
10.5.2 Context Image Classification 346
10.6 fast lifting cascade classifier
Object detection 349
10.7 scene annotation and constraint propagation 352
10.7. 1 discrete relaxation method 353
10.7.2 probability relaxation method 355
10.7.3 Search Interpretation Tree 357
10.8 semantic image segmentation and understanding 357
10.8. 1 semantic area increased by 358.
10.8.2 gene image interpretation 360
10.9 Hidden Markov Model 365
10.9. 1 application 369
10.9.2 coupled HMM 370
10.9.3 Bayesian belief network 37 1
10. 10 Gaussian mixture model and expectation maximization 372
10. 1 1 summary 378
10. 12 Reference 380
Chapter 1 1 3 d vision and geometry 389
1 1. 1 3D vision task 389
Mar theory 39 1
1 1. 1.2 Other visual categories: active and.
A clear vision 392
1 1.2 basis of projective geometry 393
1 1.2. 1 Points and Hyperplanes in Projective Space3994
1 1.2.2 should be 395.
1 1.2.3 estimating homography according to corresponding points 397
1 1.3 single-view camera 400
1 1.3. 1 camera model 400
1 1.3.2 Projection sum in homogeneous coordinate system
Back projection 402
1 1.3.3 Calibrate one from a known scene.
Camera 403
1 1.4 to reconstruct the scene 403 from multiple views.
1 1.4. 1 triangulation 403
1 1.4.2 projective reconstruction 404
1 1.4.3 matching constraint 405
1 1.4.4 beam adjustment method 406
1 1.4.5 Upgrade projection reconstruction and
Self-calibration 407
1 1.5 Dual cameras and stereo perception 408
1 1.5. 1 polar geometry-basic
Matrix 408
1 1.5.2 Relative motion of camera
-basic matrix 4 10
1 1.5.3 decompose the basic matrix into
Camera matrix 4 1 1
1 1.5.4 Estimate the basic matrix 4 1 1 from the corresponding point.
1 1.5.5 Dual camera calibration structure 4 12
1 1.5.6 revised calculation 4 14
1 1.6 Three cameras and three visual tensors 4 15
1 1.6. 1 stereo corresponding point algorithm 4 17
1 1.6.2 Actively collect range images 42 1
1 1.7 3D information of radiation measurement 423
1 1.7. 1 From Shadow to Shape 423
1 1.7.2 photometric stereo vision18000.100000000805
1 1.8 Summary 427
1 1.9 reference 428
Chapter 12 Application of 3D Vision 433
12. 1
12. 1. 1 from motion to shape 433
12. 1.2 from texture to shape 437
12. 1.3 others from x to shape
439 technology
12.2 complete 3D object 440
12.2. 1 3D objects, models and
relevant issues
12.2.2 marking 44 1
12.2.3 Volume Representation and Direct Measurement 443
12.2.4 batch modeling strategy 444
12.2.5 surface modeling strategy 446
12.2.6 is used to obtain a complete 3D model.
Panel Labeling and Fusion 447
12.3 Vision based on 3D model
12.3. 1 is generally considered as 45 1.
The drive algorithm 452
12.3.3 model-based brightness image
Surface object recognition 455
12.3.4 Distance based on vehicle type
Image recognition 456
12.4 3D view representation of 3D scene 456
12.4. 1 observation space 456
12.4.2 Multi-view representation and chart 457
12.4.3 structured as a 2D view.
Expressed geometry 457
12.4.4 displays the stored 2D view.
3D real-world scene 458
12.5 case study-from unorganized 2D
View set reconstruction 3D 460
12.6 Summary 463
12.7 Reference 464
Chapter 13 Mathematical Morphology 470
Basic concepts of morphology 470
13.2 four principles of morphology 47 1
13.3 binary expansion and corrosion 472
1 inflation 472
Corrosion 474
13.3.3 hit-miss transition 476
13.3.4 open operation and close operation 476
13.4 Gray expansion and corrosion 477
13.4. 1 top surface, shadow, gray level
Expansion and corrosion 477
13.4.2 umbra homeomorphism theorem and expansion,
Corrosion and opening and closing operations
Property 479
13.4.3 Top hat reconstruction 480
13.5 bone and object markers 48 1
13. 5. 1 homotopy transformation 8 1
13.5.2 skeleton and maximum ball 48 1
13.5.3 refinement, coarsening and homotopy skeleton 482
13.5.4 extinction function and final corrosion 485
13.5.5 Final Corrosion and Distance Function 486
13.5.6 geodetic transformation 487
13.5.7 morphological reconstruction 488
13.6 particle size determination method 489
13.7 morphological segmentation and watershed 49 1
13.7. 1 particle segmentation, labeling and summation
Watershed 49 1
13.7.2 binary morphological segmentation 49 1
13.7.3 Gray Level Segmentation and Watershed 493
13.8 Summary 494
13.9 Reference 495
Chapter 14 Image data compression 497
14. 1 image data attribute 498
14.2 discretization in image data compression
Image conversion 498
14.3 predictive compression method 500
14.4 vector quantization 502
14.5 hierarchical progressive compression method 502
Comparison of 14.6 compression methods 503
14.7 Other technologies 504
14.8 code 504
14.9 JPEG and MPEG image compression 505
14. 9. 1 JPEG- still image
Compression 505
14. 9. 2 JPEG 2000 compression 506
14. 9. 3 MPEG- full dynamic
Video compression 508
14. 10 Summary 509
Reference 5 1 1
Chapter 15 Texture 5 14
15. 1 statistical texture description 5 16
15. 1. 1 method based on spatial frequency
15. 1.2 *** Generating Matrix 5 17
15. 1.3 edge frequency 5 19
15. 1.4 Element length (strokes) 520
15. 1.5 law texture energy metric 52 1
15. 1.6 fractal texture description 52 1
15. 1.7 Multi-scale texture description
Wavelet domain method 522
15. 1.8 described by other textures.
Statistical method 525
15.2 Syntactic texture description method 526
15.2. 1 shape chain syntax 526
Graph grammar 527
15.2.3 layered texture
Original packet 528
15.3 hybrid texture description method 530
Application of 15.4 texture recognition method
15.5 Summary 53 1
15.6 Reference 532
Chapter 16 Motion analysis 537
16. 1 differential analysis method 539
16.2 optical flow 542
Optical flow calculation 542
16.2.2 global and local optical flow estimation
16.2.3 local and global integration
Optical flow estimation 546
Optical flow in motion analysis 16.2.4/kloc-0 /40666.000000060686
16.3 Analysis based on correspondence of points of interest 549
16. 3. 1 detection of interest points120066.100006868686
16.3.2 point of interest correspondence 549
16.4 detection of specific motion patterns 55 1
16.5 video tracking 554
Background modeling 554
16.5.2 Tracking based on kernel function 558
16.5.3 target path analysis 562
16.6 auxiliary tracking motion model 566
Kalman filter 567
The particulate filter 570
16.7 Summary 573
16.8 references 575
Vocabulary 58 1