search for books and compare prices
Tables of Contents for Image Processing, Analysis, and Machine Vision
Chapter/Section Title
Page #
Page Count
List of algorithms
xiii
4
List of Symbols and abbreviations
xvii
2
Preface
xix
4
Course contents
xxiii
1 Introduction
1
9
1.1 Summary
8
1
1.2 Exercises
8
1
1.3 References
9
1
2 The digitized image and its properties
10
32
2.1 Basic concepts
10
8
2.1.1 Image functions
10
3
2.1.2 The Dirac distribution and convolution
13
1
2.1.3 The Fourier transform
13
2
2.1.4 Images as a stochastic process
15
2
2.1.5 Images as linear systems
17
1
2.2 Image digitization
18
9
2.2.1 Sampling
18
4
2.2.2 Quantization
22
1
2.2.3 Color images
23
4
2.3 Digital image properties
27
10
2.3.1 Metric and topological properties of digital images
27
5
2.3.2 Histograms
32
1
2.3.3 Visual perception of the image
33
2
2.3.4 Image quality
35
1
2.3.5 Noise in images
35
2
2.4 Summary
37
1
2.5 Exercises
38
2
2.6 References
40
2
3 Data structures for image analysis
42
15
3.1 Levels of image data representation
42
1
3.2 Traditional image data structures
43
6
3.2.1 Matrices
43
2
3.2.2 Chains
45
2
3.2.3 Topological data structures
47
1
3.2.4 Relational structures
48
1
3.3 Hierarchical data structures
49
4
3.3.1 Pyramids
49
2
3.3.2 Quadtrees
51
1
3.3.3 Other pyramidical structures
52
1
3.4 Summary
53
1
3.5 Exercises
54
1
3.6 References
55
2
4 Image pre-processing
57
66
4.1 Pixel brightness transformations
58
4
4.1.1 Position-dependent brightness correction
58
1
4.1.2 Gray-scale transformation
59
3
4.2 Geometric transformations
62
6
4.2.1 Pixel co-ordinate transformations
63
2
4.2.2 Brightness interpolation
65
3
4.3 Local pre-processing
68
34
4.3.1 Image smoothing
69
8
4.3.2 Edge detectors
77
6
4.3.3 Zero-crossings of the second derivative
83
5
4.3.4 Scale in image processing
88
2
4.3.5 Canny edge detection
90
3
4.3.6 Parametric edge models
93
1
4.3.7 Edges in multi-spectral images
94
1
4.3.8 Other local pre-processing operators
94
4
4.3.9 Adaptive neighborhood pre-processing
98
4
4.4 Image restoration
102
6
4.4.1 Degradations that are easy to restore
105
1
4.4.2 Inverse filtration
106
1
4.4.3 Wiener filtration
106
2
4.5 Summary
108
3
4.6 Exercises
111
7
4.7 References
118
5
5 Segmentation
123
105
5.1 Thresholding
124
10
5.1.1 Threshold detection methods
127
1
5.1.2 Optimal thresholding
128
3
5.1.3 Multi-spectral thresholding
131
2
5.1.4 Thresholding in hierarchical data structures
133
1
5.2 Edge-based segmentation
134
42
5.2.1 Edge image thresholding
135
2
5.2.2 Edge relaxation
137
5
5.2.3 Border tracing
142
6
5.2.4 Border detection as graph searching
148
10
5.2.5 Border detection as dynamic programming
158
5
5.2.6 Hough transforms
163
10
5.2.7 Border detection using border location information
173
1
5.2.8 Region construction from borders
174
2
5.3 Region-based segmentation
176
14
5.3.1 Region merging
177
4
5.3.2 Region splitting
181
1
5.3.3 Splitting and merging
181
5
5.3.4 Watershed segmentation
186
2
5.3.5 Region growing post-processing
188
2
5.4 Matching
190
4
5.4.1 Matching criteria
191
2
5.4.2 Control strategies of matching
193
1
5.5 Advanced optimal border and surface detection approaches
194
11
5.5.1 Simultaneous detection of border pairs
194
5
5.5.2 Surface detection
199
6
5.6 Summary
205
5
5.7 Exercises
210
6
5.8 References
216
12
6 Shape representation and description
228
62
6.1 Region identification
232
3
6.2 Contour-based shape representation and description
235
19
6.2.1 Chain codes
236
1
6.2.2 Simple geometric border representation
237
3
6.2.3 Fourier transforms of boundaries
240
2
6.2.4 Boundary description using segment sequences
242
3
6.2.5 B-spline representation
245
3
6.2.6 Other contour-based shape description approaches
248
1
6.2.7 Shape invariants
249
5
6.3 Region-based shape representation and description
254
19
6.3.1 Simple scalar region descriptors
254
5
6.3.2 Moments
259
3
6.3.3 Convex hull
262
5
6.3.4 Graph representation based on region skeleton
267
4
6.3.5 Region decomposition
271
1
6.3.6 Region neighborhood graphs
272
1
6.4 Shape classes
273
1
6.5 Summary
274
2
6.6 Exercises
276
3
6.7 References
279
11
7 Object recognition
290
72
7.1 Knowledge representation
291
6
7.2 Statistical pattern recognition
297
11
7.2.1 Classification principles
298
2
7.2.2 Classifier setting
300
3
7.2.3 Classifier learning
303
4
7.2.4 Cluster analysis
307
1
7.3 Neural nets
308
7
7.3.1 Feed-forward networks
310
2
7.3.2 Unsupervised learning
312
1
7.3.3 Hopfield neural nets
313
2
7.4 Syntactic pattern recognition
315
8
7.4.1 Grammars and languages
317
2
7.4.2 Syntactic analysis, syntactic classifier
319
2
7.4.3 Syntactic classifier learning, grammar inference
321
2
7.5 Recognition as graph matching
323
5
7.5.1 Isomorphism of graphs and sub-graphs
324
4
7.5.2 Similarity of graphs
328
1
7.6 Optimization techniques in recognition
328
8
7.6.1 Genetic algorithms
330
3
7.6.2 Simulated annealing
333
3
7.7 Fuzzy systems
336
8
7.7.1 Fuzzy sets and fuzzy membership functions
336
2
7.7.2 Fuzzy set operators
338
1
7.7.3 Fuzzy reasoning
339
4
7.7.4 Fuzzy system design and training
343
1
7.8 Summary
344
3
7.9 Exercises
347
7
7.10 References
354
8
8 Image understanding
362
79
8.1 Image understanding control strategies
364
10
8.1.1 Parallel and serial processing control
364
1
8.1.2 Hierarchical control
364
1
8.1.3 Bottom-up control strategies
365
1
8.1.4 Model-based control strategies
366
1
8.1.5 Combined control strategies
367
4
8.1.6 Non-hierarchical control
371
3
8.2 Active contour models--snakes
374
6
8.3 Point distribution models
380
10
8.4 Pattern recognition methods in image understanding
390
7
8.4.1 Contextual image classification
392
5
8.5 Scene labeling and constraint propagation
397
7
8.5.1 Discrete relaxation
398
2
8.5.2 Probabilistic relaxation
400
4
8.5.3 Searching interpretation trees
404
1
8.6 Semantic image segmentation and understanding
404
13
8.6.1 Semantic region growing
406
2
8.6.2 Genetic image interpretation
408
9
8.7 Hidden Markov models
417
6
8.8 Summary
423
3
8.9 Exercises
426
2
8.10 References
428
13
9 3D vision, geometry, and radiometry
441
67
9.1 3D vision tasks
442
6
9.1.1 Marr's theory
444
2
9.1.2 Other vision paradigms: Active and purposive vision
446
2
9.2 Geometry for 3D vision
448
38
9.2.1 Basics of projective geometry
448
1
9.2.2 The single perspective camera
449
4
9.2.3 An overview of single camera calibration
453
2
9.2.4 Calibration of one camera from a known scene
455
2
9.2.5 Two cameras, stereopsis
457
3
9.2.6 The geometry of two cameras; the fundamental matrix
460
2
9.2.7 Relative motion of the camera; the essential matrix
462
2
9.2.8 Fundamental matrix estimation from image point correspondences
464
2
9.2.9 Applications of epipolar geometry in vision
466
5
9.2.10 Three and more cameras
471
5
9.2.11 Stereo correspondence algorithms
476
7
9.2.12 Active acquisition of range images
483
3
9.3 Radiometry and 3D vision
486
13
9.3.1 Radiometric considerations in determining gray-level
486
4
9.3.2 Surface reflectance
490
4
9.3.3 Shape from shading
494
4
9.3.4 Photometric stereo
498
1
9.4 Summary
499
2
9.5 Exercises
501
1
9.6 References
502
6
10 Use of 3D vision
508
51
10.1 Shape from X
508
11
10.1.1 Shape from motion
508
7
10.1.2 Shape from texture
515
2
10.1.3 Other shape from X techniques
517
2
10.2 Full 3D objects
519
16
10.2.1 3D objects, models, and related issues
519
2
10.2.2 Line labeling
521
2
10.2.3 Volumetric representation, direct measurements
523
2
10.2.4 Volumetric modeling strategies
525
2
10.2.5 Surface modeling strategies
527
2
10.2.6 Registering surface patches and their fusion to get a full 3D model
529
6
10.3 3D model-based vision
535
9
10.3.1 General considerations
535
2
10.3.2 Goad's algorithm
537
4
10.3.3 Model-based recognition of curved objects from intensity images
541
2
10.3.4 Model-based recognition based on range images
543
1
10.4 2D view-based representations of a 3D scene
544
7
10.4.1 Viewing space
544
1
10.4.2 Multi-view representations and aspect graphs
544
1
10.4.3 Geons as a 2D view-based structural representation
545
1
10.4.4 Visualizing 3D real-world scenes using stored collections of 2D views
546
5
10.5 Summary
551
1
10.6 Exercises
552
1
10.7 References
553
6
11 Mathematical morphology
559
41
11.1 Basic morphological concepts
559
2
11.2 Four morphological principles
561
2
11.3 Binary dilation and erosion
563
6
11.3.1 Dilation
563
2
11.3.2 Erosion
565
3
11.3.3 Hit-or-miss transformation
568
1
11.3.4 Opening and closing
568
1
11.4 Gray-scale dilation and erosion
569
7
11.4.1 Top surface, umbra, and gray-scale dilation and erosion
570
3
11.4.2 Umbra homeomorphism theorem, properties of erosion and dilation, opening and closing
573
1
11.4.3 Top hat transformation
574
2
11.5 Skeletons and object marking
576
13
11.5.1 Homotopic transformations
576
1
11.5.2 Skeleton, maximal ball
576
2
11.5.3 Thinning, thickening, and homotopic skeleton
578
3
11.5.4 Quench function, ultimate erosion
581
3
11.5.5 Ultimate erosion and distance functions
584
1
11.5.6 Geodesic transformations
585
1
11.5.7 Morphological reconstruction
586
3
11.6 Granulometry
589
1
11.7 Morphological segmentation and watersheds
590
5
11.7.1 Particles segmentation, marking, and watersheds
590
2
11.7.2 Binary morphological segmentation
592
2
11.7.3 Gray-scale segmentation, watersheds
594
1
11.8 Summary
595
2
11.9 Exercises
597
1
11.10 References
598
2
12 Linear discrete image transforms
600
21
12.1 Basic theory
600
2
12.2 Fourier transform
602
2
12.3 Hadamard transform
604
1
12.4 Discrete cosine transform
605
1
12.5 Wavelets
606
2
12.6 Other orthogonal image transforms
608
1
12.7 Applications of discrete image transforms
609
4
12.8 Summary
613
4
12.9 Exercises
617
2
12.10 References
619
2
13 Image data compression
621
25
13.1 Image data properties
622
1
13.2 Discrete image transforms in image data compression
623
1
13.3 Predictive compression methods
624
5
13.4 Vector quantization
629
1
13.5 Hierarchical and progressive compression methods
630
1
13.6 Comparison of compression methods
631
1
13.7 Other techniques
632
1
13.8 Coding
633
1
13.9 JPEG and MPEG image compression
634
3
13.9.1 JPEG--still image compression
634
2
13.9.2 MPEG--full-motion video compression
636
1
13.10 Summary
637
3
13.11 Exercises
640
1
13.12 References
641
5
14 Texture
646
33
14.1 Statistical texture description
649
11
14.1.1 Methods based on spatial frequencies
649
2
14.1.2 Co-occurrence matrices
651
2
14.1.3 Edge frequency
653
2
14.1.4 Primitive length (run length)
655
1
14.1.5 Laws' texture energy measures
656
1
14.1.6 Fractal texture description
657
2
14.1.7 Other statistical methods of texture description
659
1
14.2 Syntactic texture description methods
660
6
14.2.1 Shape chain grammars
661
2
14.2.2 Graph grammars
663
1
14.2.3 Primitive grouping in hierarchical textures
664
2
14.3 Hybrid texture description methods
666
1
14.4 Texture recognition method applications
667
1
14.5 Summary
668
2
14.6 Exercises
670
2
14.7 References
672
7
15 Motion analysis
679
43
15.1 Differential motion analysis methods
682
3
15.2 Optical flow
685
11
15.2.1 Optical flow computation
686
3
15.2.2 Global and local optical flow estimation
689
1
15.2.3 Optical flow computation approaches
690
3
15.2.4 Optical flow in motion analysis
693
3
15.3 Analysis based on correspondence of interest points
696
12
15.3.1 Detection of interest points
696
1
15.3.2 Correspondence of interest points
697
3
15.3.3 Object tracking
700
8
15.4 Kalman filters
708
2
15.4.1 Example
709
1
15.5 Summary
710
2
15.6 Exercises
712
2
15.7 References
714
8
16 Case studies
722
33
16.1 An optical music recognition system
722
5
16.2 Automated image analysis in cardiology
727
11
16.2.1 Robust analysis of coronary angiograms
730
3
16.2.2 Knowledge-based analysis of intra-vascular ultrasound
733
5
16.3 Automated identification of airway trees
738
6
16.4 Passive surveillance
744
6
16.5 References
750
5
Index
755