Feature Extraction & Image Processing
Regular price
29.750 KD
inc. VAT
Couldn't load pickup availability
Table of contents
- Title pageiii
- Copyright Pageiv
- Table of Contentsv
- Prefacexi
- Chapter 1 Introduction1
- 1.1 Overview1
- 1.2 Human and computer vision1
- 1.3 The human vision system3
- 1.3.1 The eye4
- 1.3.2 The neural system6
- 1.3.3 Processing7
- 1.4 Computer vision systems9
- 1.4.1 Cameras10
- 1.4.2 Computer interfaces12
- 1.4.3 Processing an image14
- 1.5 Mathematical systems15
- 1.5.1 Mathematical tools16
- 1.5.2 Hello Mathcad, hello images!16
- 1.5.3 Hello Matlab!21
- 1.6 Associated literature24
- 1.6.1 Journals and magazines24
- 1.6.2 Textbooks25
- 1.6.3 The web28
- 1.7 Conclusions29
- 1.8 References29
- Chapter 2 Images, sampling and frequency domain processing33
- 2.1 Overview33
- 2.2 Image formation34
- 2.3 The Fourier transform37
- 2.4 The sampling criterion43
- 2.5 The discrete Fourier transform47
- 2.5.1 One-dimensional transform47
- 2.5.2 Two-dimensional transform49
- 2.6 Other properties of the Fourier transform54
- 2.6.1 Shift invariance54
- 2.6.2 Rotation56
- 2.6.3 Frequency scaling56
- 2.6.4 Superposition (linearity)57
- 2.7 Transforms other than Fourier58
- 2.7.1 Discrete cosine transform58
- 2.7.2 Discrete Hartley transform59
- 2.7.3 Introductory wavelets: the Gabor wavelet61
- 2.7.4 Other transforms63
- 2.8 Applications using frequency domain properties64
- 2.9 Further reading65
- 2.10 References66
- Chapter 3 Basic image processing operations69
- 3.1 Overview69
- 3.2 Histograms70
- 3.3 Point operators71
- 3.3.1 Basic point operations71
- 3.3.2 Histogram normalization74
- 3.3.3 Histogram equalization75
- 3.3.4 Thresholding77
- 3.4 Group operations81
- 3.4.1 Template convolution81
- 3.4.2 Averaging operator84
- 3.4.3 On different template size87
- 3.4.4 Gaussian averaging operator88
- 3.5 Other statistical operators90
- 3.5.1 More on averaging90
- 3.5.2 Median filter91
- 3.5.3 Mode filter94
- 3.5.4 Anisotropic diffusion96
- 3.5.5 Force field transform101
- 3.5.6 Comparison of statistical operators102
- 3.6 Mathematical morphology103
- 3.6.1 Morphological operators104
- 3.6.2 Grey-level morphology107
- 3.6.3 Grey-level erosion and dilation108
- 3.6.4 Minkowski operators109
- 3.7 Further reading112
- 3.8 References113
- Chapter 4 Low-level feature extraction (including edge detection)115
- 4.1 Overview115
- 4.2 First order edge detection operators117
- 4.2.1 Basic operators117
- 4.2.2 Analysis of the basic operators119
- 4.2.3 Prewitt edge detection operator121
- 4.2.4 Sobel edge detection operator123
- 4.2.5 Canny edge detection operator129
- 4.3 Second order edge detection operators137
- 4.3.1 Motivation137
- 4.3.2 Basic operators: the Laplacian137
- 4.3.3 Marr–Hildreth operator139
- 4.4 Other edge detection operators144
- 4.5 Comparison of edge detection operators145
- 4.6 Further reading on edge detection146
- 4.7 Phase congruency147
- 4.8 Localized feature extraction152
- 4.8.1 Detecting image curvature (corner extraction)153
- 4.8.1.1 Definition of curvature153
- 4.8.1.2 Computing differences in edge direction154
- 4.8.1.3 Measuring curvature by changes in intensity (differentiation)156
- 4.8.1.4 Moravec and Harris detectors159
- 4.8.1.5 Further reading on curvature163
- 4.8.2 Modern approaches: region/patch analysis163
- 4.8.2.1 Scale invariant feature transform163
- 4.8.2.2 Saliency166
- 4.8.2.3 Other techniques and performance issues167
- 4.9 Describing image motion167
- 4.9.1 Area-based approach168
- 4.9.2 Differential approach171
- 4.9.3 Further reading on optical flow177
- 4.10 Conclusions178
- 4.11 References178
- Chapter 5 Feature extraction by shape matching183
- 5.1 Overview183
- 5.2 Thresholding and subtraction184
- 5.3 Template matching186
- 5.3.1 Definition186
- 5.3.2 Fourier transform implementation193
- 5.3.3 Discussion of template matching196
- 5.4 Hough transform196
- 5.4.1 Overview196
- 5.4.2 Lines197
- 5.4.3 Hough transform for circles203
- 5.4.4 Hough transform for ellipses207
- 5.4.5 Parameter space decomposition210
- 5.4.5.1 Parameter space reduction for lines210
- 5.4.5.2 Parameter space reduction for circles212
- 5.4.5.3 Parameter space reduction for ellipses217
- 5.5 Generalized Hough transform221
- 5.5.1 Formal definition of the GHT221
- 5.5.2 Polar definition223
- 5.5.3 The GHT technique224
- 5.5.4 Invariant GHT228
- 5.6 Other extensions to the Hough transform235
- 5.7 Further reading236
- 5.8 References237
- Chapter 6 Flexible shape extraction (snakes and other techniques)241
- 6.1 Overview241
- 6.2 Deformable templates242
- 6.3 Active contours (snakes)244
- 6.3.1 Basics244
- 6.3.2 The greedy algorithm for snakes246
- 6.3.3 Complete (Kass) snake implementation252
- 6.3.4 Other snake approaches257
- 6.3.5 Further snake developments257
- 6.3.6 Geometric active contours261
- 6.4 Shape skeletonization266
- 6.4.1 Distance transforms266
- 6.4.2 Symmetry268
- 6.5 Flexible shape models: active shape and active appearance272
- 6.6 Further reading275
- 6.7 References276
- Chapter 7 Object description281
- 7.1 Overview281
- 7.2 Boundary descriptions282
- 7.2.1 Boundary and region282
- 7.2.2 Chain codes283
- 7.2.3 Fourier descriptors285
- 7.2.3.1 Basis of Fourier descriptors286
- 7.2.3.2 Fourier expansion287
- 7.2.3.3 Shift invariance289
- 7.2.3.4 Discrete computation290
- 7.2.3.5 Cumulative angular function292
- 7.2.3.6 Elliptic Fourier descriptors301
- 7.2.3.7 Invariance305
- 7.3 Region descriptors311
- 7.3.1 Basic region descriptors311
- 7.3.2 Moments315
- 7.3.2.1 Basic properties315
- 7.3.2.2 Invariant moments318
- 7.3.2.3 Zernike moments320
- 7.3.2.4 Other moments324
- 7.4 Further reading325
- 7.5 References326
- Chapter 8 Introduction to texture description, segmentation and classification329
- 8.1 Overview329
- 8.2 What is texture?330
- 8.3 Texture description332
- 8.3.1 Performance requirements332
- 8.3.2 Structural approaches332
- 8.3.3 Statistical approaches335
- 8.3.4 Combination approaches337
- 8.4 Classification339
- 8.4.1 The k-nearest neighbour rule339
- 8.4.2 Other classification approaches343
- 8.5 Segmentation343
- 8.6 Further reading345
- 8.7 References346
- Chapter 9 Appendix 1: Example worksheets349
- 9.1 Example Mathcad worksheet for Chapter 3349
- 9.2 Example Matlab worksheet for Chapter 4352
- Chapter 10 Appendix 2: Camera geometry fundamentals355
- 10.1 Image geometry355
- 10.2 Perspective camera355
- 10.3 Perspective camera model357
- 10.3.1 Homogeneous coordinates and projective geometry357
- 10.3.1.1 Representation of a line and duality358
- 10.3.1.2 Ideal points358
- 10.3.1.3 Transformations in the projective space359
- 10.3.2 Perspective camera model analysis360
- 10.3.3 Parameters of the perspective camera model363
- 10.4 Affine camera364
- 10.4.1 Affine camera model365
- 10.4.2 Affine camera model and the perspective projection366
- 10.4.3 Parameters of the affine camera model368
- 10.5 Weak perspective model369
- 10.6 Example of camera models371
- 10.7 Discussion379
- 10.8 References380
- Chapter 11 Appendix 3: Least squares analysis381
- 11.1 The least squares criterion381
- 11.2 Curve fitting by least squares382
- Chapter 12 Appendix 4: Principal components analysis385
- 12.1 Introduction385
- 12.2 Data385
- 12.3 Covariance386
- 12.4 Covariance matrix388
- 12.5 Data transformation389
- 12.6 Inverse transformation390
- 12.7 Eigenproblem391
- 12.8 Solving the eigenproblem392
- 12.9 PCA method summary392
- 12.10 Example393
- 12.11 References398
- Index399
Whilst other books cover a broad range of topics, Feature Extraction and Image Processing takes one of the prime targets of applied computer vision, feature extraction, and uses it to provide an essential guide to the implementation of image processing and computer vision techniques.
Acting as both a source of reference and a student text, the book explains techniques and fundamentals in a clear and concise manner and helps readers to develop working techniques, with usable code provided throughout. The new edition is updated throughout in line with developments in the field, and is revised to focus on mathematical programming in Matlab.
* Essential reading for engineers and students working in this cutting edge field
* Ideal module text and background reference for courses in image processing and computer vision
* Companion website includes worksheets, links to free software, Matlab files and solutions
Acting as both a source of reference and a student text, the book explains techniques and fundamentals in a clear and concise manner and helps readers to develop working techniques, with usable code provided throughout. The new edition is updated throughout in line with developments in the field, and is revised to focus on mathematical programming in Matlab.
* Essential reading for engineers and students working in this cutting edge field
* Ideal module text and background reference for courses in image processing and computer vision
* Companion website includes worksheets, links to free software, Matlab files and solutions