Feature Extraction & Image Processing for Computer Vision: Extended Contents List

Extended Contents List

Preface ............................................................................................................................................. xi
About the authors ......................................................................................................................... xvii

CHAPTER 1 Introduction 1
1.1 Overview............................................................................................................................ 1
1.2 Human and Computer Vision .......................................................................................... 2
1.3 The Human Vision System ............................................................................................... 4
1.3.1 The Eye .................................................................................................................................... 5
1.3.2 The Neural System .................................................................................................................. 8
1.3.3 Processing ................................................................................................................................ 9
1.4 Computer Vision Systems ............................................................................................... 12
1.4.1 Cameras ................................................................................................................................. 12
1.4.2 Computer Interfaces.............................................................................................................. 15
1.4.3 Processing an Image ............................................................................................................. 17
1.5 Mathematical Systems ................................................................................................... 19
1.5.1 Mathematical Tools .............................................................................................................. 19
1.5.2 Hello Matlab, Hello Images! ................................................................................................. 20
1.5.3 Hello Mathcad! ...................................................................................................................... 25
1.6 Associated Literature ...................................................................................................... 30
1.6.1 Journals, Magazines and Conferences ................................................................................... 30
1.6.2 Textbooks .............................................................................................................................. 31
1.6.3 The Web ................................................................................................................................ 34
1.7 Conclusions ...................................................................................................................... 35
1.8 Chapter 1 References ...................................................................................................... 35

CHAPTER 2 Images, Sampling and Frequency Domain Processing 37

2.1 Overview........................................................................................................................... 37
2.2 Image Formation ............................................................................................................. 38
2.3 The Fourier Transform.................................................................................................. 42
2.4 The Sampling Criterion .................................................................................................. 49
2.5 The Discrete Fourier Transform (DFT) ....................................................................... 53
2.5.1 One Dimensional Transform ................................................................................... 53
2.5.2 Two Dimensional Transform ................................................................................... 57
2.6 Other Properties of the Fourier Transform.................................................................. 63
2.6.1 Shift Invariance ........................................................................................................ 63
2.6.2 Rotation .................................................................................................................... 65
2.6.3 Frequency Scaling .................................................................................................... 66
2.6.4 Superposition (Linearity) ......................................................................................... 67
2.7 Transforms other than Fourier ...................................................................................... 68
2.7.1 Discrete Cosine Transform ....................................................................................... 68
2.7.2 Discrete Hartley Transform ...................................................................................... 70
2.7.3 Introductory Wavelets .............................................................................................. 71
2.7.3.1 Gabor Wavelet ................................................................................................ 71
2.7.3.2 Haar Wavelet ................................................................................................... 74
i
Feature Extraction & Image Processing for Computer Vision: Extended Contents List

2.7.4 Other Transforms .................................................................................................... 78

2.8 Applications using Frequency Domain Properties ....................................................... 78
2.9 Further Reading .............................................................................................................. 80
2.10 Chapter 2 References .................................................................................................... 81

CHAPTER 3 Basic Image Processing Operations 83

3.1 Overview.......................................................................................................................... 83
3.2 Histograms ....................................................................................................................... 84
3.3 Point Operators ............................................................................................................... 86
3.3.1 Basic Point Operations .......................................................................................................... 86
3.3.2 Histogram Normalisation....................................................................................................... 89
3.3.3 Histogram Equalisation ......................................................................................................... 90
3.3.4 Thresholding .......................................................................................................................... 93
3.4 Group Operations............................................................................................................ 98
3.4.1 Template Convolution ........................................................................................................... 98
3.4.2 Averaging Operator ............................................................................................................. 101
3.4.3 On Different Template Size ................................................................................................. 103
3.4.4 Gaussian Averaging Operator.............................................................................................. 104
3.4.5 More on Averaging .............................................................................................................. 107
3.5 Other Statistical Operators .......................................................................................... 109
3.5.1 Median Filter ....................................................................................................................... 109
3.5.2 Mode Filter .......................................................................................................................... 112
3.5.3 Anisotropic Diffusion .......................................................................................................... 114
3.5.4 Force Field Transform ......................................................................................................... 121
3.5.5 Comparison of Statistical Operators ................................................................................... 122
3.6 Mathematical Morphology ........................................................................................... 123
3.6.1 Morphological Operators ..................................................................................................... 124
3.6.2 Grey Level Morphology ...................................................................................................... 127
3.6.3 Grey Level Erosion and Dilation ......................................................................................... 128
3.6.4 Minkowski Operators .......................................................................................................... 130
3.7 Further Reading ............................................................................................................ 134
3.8 Chapter 3 References .................................................................................................... 134

CHAPTER 4 Low-Level Feature Extraction (including Edge Detection) 137

4.1 Overview.......................................................................................................................... 138
4.2 Edge Detection .............................................................................................................. 140
4.2.1 First Order Edge Detection Operators ................................................................ 140
4.2.1.1 Basic Operators ............................................................................................. 140
4.2.1.2 Analysis of the Basic Operators..................................................................... 142
4.2.1.3 Prewitt Edge Detection Operator .................................................................. 145
4.2.1.4 Sobel Edge Detection Operator ..................................................................... 146
4.2.1.5 The Canny Edge Detector .............................................................................. 153
4.2.2 Second Order Edge Detection Operators ................................................................ 161
4.2.2.1 Motivation ...................................................................................................... 161
4.2.2.2 Basic Operators: The Laplacian.................................................................... 163
4.2.2.3 The Marr-Hildreth Operator ........................................................................ 165
4.2.3 Other Edge Detection Operators ............................................................................. 170
4.2.4 Comparison of Edge Detection Operators.............................................................. 171
ii
Feature Extraction & Image Processing for Computer Vision: Extended Contents List

4.2.5 Further Reading on Edge Detection ....................................................................... 173

4.3 Phase Congruency ......................................................................................................... 173
4.4 Localised Feature Extraction ....................................................................................... 180
4.4.1 Detecting Image Curvature (Corner Extraction) .................................................... 180
4.4.1.1 Definition of Curvature ................................................................................... 180
4.4.1.2 Computing Differences in Edge Direction...................................................... 182
4.4.1.3 Measuring Curvature by Changes in Intensity (Differentiation).................... 184
4.4.1.4 Moravec and Harris Detectors ....................................................................... 188
4.4.1.5 Further Reading on Curvature ....................................................................... 192
4.4.2 Modern Approaches; Region/Patch Analysis......................................................... 193
4.4.2.1 Scale Invariant Feature Transform (SIFT) ...................................................... 193
4.4.2.2 Speeded Up Robust Features (SURF) ............................................................. 196
4.4.2.3 Saliency ............................................................................................................ 198
4.4.2.4 Other Techniques and Performance Issues ..................................................... 198
4.5 Describing Image Motion ............................................................................................ 199
4.5.1 Area-based approach .............................................................................................. 200
4.5.2 Differential approach .............................................................................................. 204
4.5.3 Further Reading on Optical Flow ........................................................................... 211
4.6 Further Reading ............................................................................................................ 212
4.7 Chapter 4 References .................................................................................................... 212

CHAPTER 5 High-Level Feature Extraction: Fixed Shape Matching ................. 217

5.1 Overview......................................................................................................................... 218
5.2 Thresholding and Subtraction ..................................................................................... 220
5.3 Template Matching ....................................................................................................... 222
5.3.1 Definition................................................................................................................ 222
5.3.2 Fourier Transform Implementation ........................................................................ 230
5.3.3 Discussion of Template Matching ......................................................................... 234
5.4 Feature Extraction by Low Level Features ................................................................ 235
5.4.1 Appearance-Based Approaches .............................................................................. 235
5.4.1.1 Object Detection by Templates ....................................................................... 235
5.4.1.2 Object Detection by Combinations of Parts ................................................... 237
5.4.2 Distribution-Based Descriptors .............................................................................. 238
5.4.2.1 Description by Interest Points ........................................................................ 238
5.4.2.2 Characterising Object Appearance and Shape .............................................. 241
5.5 Hough Transform (HT) ................................................................................................ 243
5.5.1 Overview ................................................................................................................ 243
5.5.2 Lines ..................................................................................................................... 243
5.5.3 HT for Circles ........................................................................................................ 250
5.5.4 HT for Ellipses ...................................................................................................... 255
5.5.5 Parameter Space Decomposition ............................................................................ 258
5.5.5.1 Parameter space reduction for lines ............................................................... 259
5.5.5.2 Parameter space reduction for circles............................................................ 261
5.5.5.3 Parameter space reduction for ellipses .......................................................... 266
5.5.6 Generalised Hough Transform (GHT) .................................................................. 271
5.5.6.1 Formal Definition of the GHT ........................................................................ 272
5.5.6.2 Polar definition ............................................................................................... 273
5.5.6.3 The GHT Technique ........................................................................................ 274
iii
Feature Extraction & Image Processing for Computer Vision: Extended Contents List

5.5.6.4 Invariant GHT................................................................................................. 279

5.5.7 Other Extensions to the HT ................................................................................... 287
5.6 Further Reading ............................................................................................................ 288
5.7 Chapter 5 References .................................................................................................... 280

CHAPTER 6 High-Level Feature Extraction: Deformable Shape Analysis 293

6.1 Overview......................................................................................................................... 293
6.2 Deformable Shape Analysis .......................................................................................... 294
6.2.1 Deformable Templates ........................................................................................... 294
6.2.2 Parts-based Shape Analysis .................................................................................... 297
6.3 Active Contours (Snakes) ............................................................................................. 299
6.3.1 Basics...................................................................................................................... 299
6.3.2 The Greedy Algorithm for Snakes ......................................................................... 301
6.3.3 Complete (Kass) Snake Implementation ................................................................ 308
6.3.4 Other Snake Approaches ........................................................................................ 313
6.3.5 Further Snake Developments ................................................................................. 314
6.3.6 Geometric Active Contours (Level-Set Based Approaches) .................................. 318
6.4 Shape Skeletonisation................................................................................................... 325
6.4.1 Distance Transforms............................................................................................... 325
6.4.2 Symmetry ............................................................................................................... 327
6.5 Flexible Shape Models – Active Shape and Active Appearance ............................... 334
6.6 Further Reading ............................................................................................................ 338
6.7 Chapter 6 References .................................................................................................... 338

CHAPTER 7 Object Description 343

7.1 Overview...................................................................................................................... 343
7.2 Boundary Descriptions............................................................................................... 345
7.2.1 Boundary and Region ........................................................................................... 345
7.2.2 Chain Codes ......................................................................................................... 346
7.2.3 Fourier Descriptors .............................................................................................. 349
7.2.3.1 Basis of Fourier Descriptors............................................................................ 350
7.2.3.2 Fourier Expansion ........................................................................................... 351
7.2.3.3 Shift invariance ................................................................................................ 354
7.2.3.4 Discrete computation ....................................................................................... 355
7.2.3.5 Cumulative Angular Function .......................................................................... 357
7.2.3.6 Elliptic Fourier Descriptors............................................................................. 369
7.2.3.7 Invariance ........................................................................................................ 372
7.3 Region Descriptors .................................................................................................... 378
7.3.1 Basic Region Descriptors .................................................................................... 378
7.3.2 Moments .............................................................................................................. 383
7.3.2.1 Basic Properties .............................................................................................. 383
7.3.2.2 Invariant Moments .......................................................................................... 387
7.3.2.3 Zernike Moments ............................................................................................. 388
7.3.2.4 Other Moments ................................................................................................ 393
7.4 Further Reading ........................................................................................................ 395
7.5 Chapter 7 References ................................................................................................ 395

iv
Feature Extraction & Image Processing for Computer Vision: Extended Contents List

CHAPTER 8 Intro. to Texture Description, Segmentation and Classification 399

8.1 Overview........................................................................................................................ 399
8.2 What is Texture? ......................................................................................................... 400
8.3 Texture Description ....................................................................................................... 403
8.3.1 Performance Requirements .................................................................................... 403
8.3.2 Structural Approaches ............................................................................................ 403
8.3.3 Statistical Approaches ............................................................................................ 406
8.3.4 Combination Approaches ....................................................................................... 409
8.3.5 Local Binary Patterns ............................................................................................. 411
8.3.6 Other Approaches ................................................................................................... 417
8.4 Classification .................................................................................................................. 417
8.4.1 Distance Measures .................................................................................................. 417
8.4.2 The k-Nearest Neighbour Rule ............................................................................... 424
8.4.3 Other Classification Approaches ............................................................................ 428
8.5 Segmentation .................................................................................................................. 429
8.6 Further Reading ............................................................................................................ 431
8.7 Chapter 8 References .................................................................................................... 432

CHAPTER 9 Moving Object Detection and Description 435

9.1 Overview ....................................................................................................................................... 435
9.2 Moving Object Detection .............................................................................................................. 437
9.2.1 Basic Approaches ................................................................................................................ 437
9.2.1.1 Detection by Subtracting the Background .................................................................. 437
9.2.1.2 Improving Quality by Morphology ............................................................................. 440
9.2.2 Modelling and Adapting to the (Static) Background ........................................................... 442
9.2.3 Background Segmentation by Thresholding........................................................................ 447
9.2.4 Problems and Advances ....................................................................................................... 450
9.3 Tracking Moving Features ............................................................................................................ 451
9.3.1 Tracking Moving Objects .................................................................................................... 451
9.3.2 Tracking by Local Search .................................................................................................... 452
9.3.3 Problems in Tracking ........................................................................................................... 455
9.3.4 Approaches to Tracking ....................................................................................................... 455
9.3.5 MeanShift and Camshift ....................................................................................................... 457
9.3.5.1 Kernel-Based Density Estimation ............................................................................... 457
9.3.5.2 MeanShift Tracking ..................................................................................................... 461
9.3.5.3 Camshift Technique ..................................................................................................... 467
9.3.6 Recent Approaches .............................................................................................................. 472
9.4 Moving Feature Extraction and Description ................................................................................. 474
9.4.1 Moving (Biological) Shape Analysis ................................................................................... 474
9.4.2 Detecting Moving Shapes by Shape Matching in Image Sequences ................................... 476
9.4.3 Moving Shape Description .................................................................................................. 480
9.5 Further Reading ............................................................................................................................. 484
9.6 Chapter 9 References .................................................................................................................... 484

CHAPTER 10 Appendix 1: Camera Geometry Fundamentals 489

10.1 Image Geometry................................................................................................................................
10.2 Perspective Camera ...........................................................................................................................
10.3 Perspective Camera Model ...............................................................................................................
v
Feature Extraction & Image Processing for Computer Vision: Extended Contents List

10.3.1 Homogeneous co-ordinates and Projective Geometry .............................................................

10.3.1.1 Representation of a Line and Duality ..............................................................................
10.3.1.2 Ideal Points ......................................................................................................................
10.3.1.3 Transformations in the Projective Space .........................................................................
10.3.2 Perspective Camera Model Analysis .......................................................................................
10.3.3 Parameters of the Perspective Camera Model .........................................................................
10.4 Affine Camera ...................................................................................................................................
10.4.1 Affine Camera Model ..............................................................................................................
10.4.2 Affine Camera Model and the Perspective Projection .............................................................
10.4.3 Parameters of the Affine Camera Model .................................................................................
10.5 Weak Perspective Model ..................................................................................................................
10.6 Example of Camera Models..............................................................................................................
10.7 Discussion .........................................................................................................................................
10.8 Appendix 1 References .....................................................................................................................

CHAPTER 11 Appendix 2: Least Squares Analysis 519

11.1 The Least Squares Criterion .............................................................................................................
11.2 Curve Fitting by Least Squares ........................................................................................................

CHAPTER 12 Appendix 3: Principal Components Analysis 525

12.1 Principal Components Analysis (PCA) ............................................................................................
12.2 Data ..................................................................................................................................................
12.3 Covariance .......................................................................................................................................
12.4 Covariance Matrix............................................................................................................................
12.5 Data Transformation ........................................................................................................................
12.6 Inverse Transformation ....................................................................................................................
12.7 Eigenproblem ...................................................................................................................................
12.8 Solving the Eigenproblem ................................................................................................................
12.9 PCA Method Summary ....................................................................................................................
12.10 Example .........................................................................................................................................
12.11 Appendix 4 References ..................................................................................................................

CHAPTER 13 Appendix 4: Colour Images 541

13.1 Colour Images
13.2 Tristimulus Theory
13.3 Colour Models
13.3.1 The Colorimetric Equation .........................................................................................
13.3.2 Luminosity Function ..................................................................................................
13.3.3 Perception based Colour Models: The CIE RGB and CIE XYZ ...............................
13.3.3.1 CIE RGB Colour Model: Wright-Guild Data ................................................................
13.3.3.2. CIE RGB Colour Matching Functions ..........................................................................
13.3.3.3 CIE RGB Chromaticity Diagram and Chromaticity Coordinates .................................
13.3.3.4 CIE XYZ Colour Model ..................................................................................................
13.3.3.5 CIE XYZ Colour Matching Functions ............................................................................
13.3.3.6 XYZ Chromaticity Diagram ...........................................................................................
13.3.4 Uniform Colour Spaces: CIE LUV and CIE LAB .....................................................

vi
Feature Extraction & Image Processing for Computer Vision: Extended Contents List

13.3.5 Additive and Subtractive Colour Models: RGB and CMY ........................................
13.3.5.1 RGB and CMY................................................................................................................
13.3.5.2 Transformation between RGB Colour Models ...............................................................
13.3.5.3 Transformation between RGB and CMY Colour Models ..............................................
13.3.6 Luminance and Chrominance Colour Models: YUV, YIQ and YCbCr ....................
13.3.6.1 Luminance and Gamma Correction ...............................................................................
13.3.6.2 Chrominance ..................................................................................................................
13.3.6.3 Transformations between YUV, YIQ and RGB Colour Models .....................................
13.3.6.4 Colour Model for Component Video: YPbPr .................................................................
13.3.6.5 Colour Model for Digital Video: YCbCr .......................................................................
13.3.7 Perceptual Colour Models: HSV and HLS ................................................................
13.3.7.1 The Hexagonal Model: HSV ..........................................................................................
13.3.7.2 The Triangular Model: HSI ...........................................................................................
13.3.8 More Colour Models ..................................................................................................
13.4 References ............................................................................................................................

Index ............................................................................................................................................ 601

vii