Flexible Manipulators : Modeling, Analysis and Optimum Design

Description

0i_Front-matter......Page 1 Feature Extraction & Image Processing for Computer Vision......Page 3 Dedication......Page 4 Copyright page......Page 5 Why did we write this book?......Page 6 The book and its support......Page 7 In gratitude......Page 10 Final message......Page 11 About the authors......Page 12 1.1 Overview......Page 13 1.2 Human and computer vision......Page 14 1.3 The human vision system......Page 16 1.3.1 The eye......Page 17 1.3.2 The neural system......Page 20 1.3.3 Processing......Page 21 1.4.1 Cameras......Page 24 1.4.2 Computer interfaces......Page 27 1.4.3 Processing an image......Page 29 1.5.1 Mathematical tools......Page 31 1.5.2 Hello Matlab, hello images!......Page 32 1.5.3 Hello Mathcad!......Page 37 1.6.1 Journals, magazines, and conferences......Page 42 1.6.2 Textbooks......Page 43 1.6.3 The Web......Page 46 1.8 References......Page 47 2.1 Overview......Page 49 2.2 Image formation......Page 50 2.3 The Fourier transform......Page 54 2.4 The sampling criterion......Page 61 2.5.1 1D transform......Page 65 2.5.2 2D transform......Page 69 2.6.1 Shift invariance......Page 75 2.6.2 Rotation......Page 77 2.6.3 Frequency scaling......Page 78 2.6.4 Superposition (linearity)......Page 79 2.7.1 Discrete cosine transform......Page 80 2.7.2 Discrete Hartley transform......Page 82 2.7.3.1 Gabor wavelet......Page 83 2.7.3.2 Haar wavelet......Page 86 2.8 Applications using frequency domain properties......Page 90 2.9 Further reading......Page 92 2.10 References......Page 93 3.1 Overview......Page 95 3.2 Histograms......Page 96 3.3.1 Basic point operations......Page 98 3.3.2 Histogram normalization......Page 101 3.3.3 Histogram equalization......Page 102 3.3.4 Thresholding......Page 105 3.4.1 Template convolution......Page 110 3.4.2 Averaging operator......Page 113 3.4.3 On different template size......Page 115 3.4.4 Gaussian averaging operator......Page 116 3.4.5 More on averaging......Page 119 3.5.1 Median filter......Page 121 3.5.2 Mode filter......Page 124 3.5.3 Anisotropic diffusion......Page 126 3.5.4 Force field transform......Page 133 3.5.5 Comparison of statistical operators......Page 134 3.6 Mathematical morphology......Page 135 3.6.1 Morphological operators......Page 136 3.6.2 Gray-level morphology......Page 139 3.6.3 Gray-level erosion and dilation......Page 140 3.6.4 Minkowski operators......Page 142 3.8 References......Page 146 4 Low-level feature extraction (including edge detection)......Page 149 4.1 Overview......Page 150 4.2.1.1 Basic operators......Page 152 4.2.1.2 Analysis of the basic operators......Page 154 4.2.1.3 Prewitt edge-detection operator......Page 157 4.2.1.4 Sobel edge-detection operator......Page 158 4.2.1.5 The Canny edge detector......Page 165 4.2.2.1 Motivation......Page 173 4.2.2.2 Basic operators: the Laplacian......Page 175 4.2.2.3 The Marr–Hildreth operator......Page 177 4.2.3 Other edge-detection operators......Page 182 4.2.4 Comparison of edge-detection operators......Page 183 4.3 Phase congruency......Page 185 4.4.1.1 Definition of curvature......Page 192 4.4.1.2 Computing differences in edge direction......Page 194 4.4.1.3 Measuring curvature by changes in intensity (differentiation)......Page 196 4.4.1.4 Moravec and Harris detectors......Page 200 4.4.1.5 Further reading on curvature......Page 204 4.4.2.1 Scale invariant feature transform......Page 205 4.4.2.2 Speeded up robust features......Page 208 4.4.2.4 Other techniques and performance issues......Page 210 4.5 Describing image motion......Page 211 4.5.1 Area-based approach......Page 212 4.5.2 Differential approach......Page 216 4.5.3 Further reading on optical flow......Page 223 4.7 References......Page 224 Chapter 5 High-level feature extraction: fixed shape matching......Page 229 5.1 Overview......Page 230 5.2 Thresholding and subtraction......Page 232 5.3.1 Definition......Page 234 5.3.2 Fourier transform implementation......Page 242 5.3.3 Discussion of template matching......Page 246 5.4.1.1 Object detection by templates......Page 247 5.4.1.2 Object detection by combinations of parts......Page 249 5.4.2.1 Description by interest points......Page 250 5.4.2.2 Characterizing object appearance and shape......Page 253 5.5.2 Lines......Page 255 5.5.3 HT for circles......Page 262 5.5.4 HT for ellipses......Page 267 5.5.5 Parameter space decomposition......Page 270 5.5.5.1 Parameter space reduction for lines......Page 271 5.5.5.2 Parameter space reduction for circles......Page 273 5.5.5.3 Parameter space reduction for ellipses......Page 278 5.5.6 Generalized HT......Page 283 5.5.6.1 Formal definition of the GHT......Page 284 5.5.6.2 Polar definition......Page 285 5.5.6.3 The GHT technique......Page 286 5.5.6.4 Invariant GHT......Page 291 5.5.7 Other extensions to the HT......Page 299 5.6 Further reading......Page 300 5.7 References......Page 301 6.1 Overview......Page 304 6.2.1 Deformable templates......Page 305 6.2.2 Parts-based shape analysis......Page 308 6.3.1 Basics......Page 310 6.3.2 The Greedy algorithm for snakes......Page 312 6.3.3 Complete (Kass) snake implementation......Page 319 6.3.4 Other snake approaches......Page 324 6.3.5 Further snake developments......Page 325 6.3.6 Geometric active contours (level-set-based approaches)......Page 329 6.4.1 Distance transforms......Page 336 6.4.2 Symmetry......Page 338 6.5 Flexible shape models—active shape and active appearance......Page 345 6.7 References......Page 349 7.1 Overview......Page 354 7.2.1 Boundary and region......Page 356 7.2.2 Chain codes......Page 357 7.2.3 Fourier descriptors......Page 360 7.2.3.1 Basis of Fourier descriptors......Page 361 7.2.3.2 Fourier expansion......Page 362 7.2.3.3 Shift invariance......Page 365 7.2.3.4 Discrete computation......Page 366 7.2.3.5 Cumulative angular function......Page 368 7.2.3.6 Elliptic Fourier descriptors......Page 380 7.2.3.7 Invariance......Page 383 7.3.1 Basic region descriptors......Page 389 7.3.2.1 Basic properties......Page 394 7.3.2.2 Invariant moments......Page 398 7.3.2.3 Zernike moments......Page 399 7.3.2.4 Other moments......Page 404 7.5 References......Page 406 8.1 Overview......Page 409 8.2 What is texture?......Page 410 8.3.2 Structural approaches......Page 413 8.3.3 Statistical approaches......Page 416 8.3.4 Combination approaches......Page 419 8.3.5 Local binary patterns......Page 421 8.4.1 Distance measures......Page 427 8.4.2 The k-nearest neighbor rule......Page 434 8.4.3 Other classification approaches......Page 438 8.5 Segmentation......Page 439 8.6 Further reading......Page 441 8.7 References......Page 442 9.1 Overview......Page 445 9.2.1.1 Detection by subtracting the background......Page 447 9.2.1.2 Improving quality by morphology......Page 450 9.2.2 Modeling and adapting to the (static) background......Page 452 9.2.3 Background segmentation by thresholding......Page 457 9.2.4 Problems and advances......Page 460 9.3.1 Tracking moving objects......Page 461 9.3.2 Tracking by local search......Page 462 9.3.4 Approaches to tracking......Page 465 9.3.5.1 Kernel-based density estimation......Page 467 Similarity function......Page 471 Kernel profiles and shadow kernels......Page 474 Gradient maximization......Page 475 9.3.5.3 Camshift technique......Page 477 9.3.6 Recent approaches......Page 482 9.4.1 Moving (biological) shape analysis......Page 484 9.4.2 Detecting moving shapes by shape matching in image sequences......Page 486 9.4.3 Moving shape description......Page 490 9.5 Further reading......Page 493 9.6 References......Page 494 10.1 Image geometry......Page 498 10.2 Perspective camera......Page 499 10.3.1 Homogeneous coordinates and projective geometry......Page 500 10.3.1.1 Representation of a line and duality......Page 501 10.3.1.2 Ideal points......Page 502 10.3.1.3 Transformations in the projective space......Page 503 10.3.2 Perspective camera model analysis......Page 505 10.3.3 Parameters of the perspective camera model......Page 508 10.4 Affine camera......Page 509 10.4.1 Affine camera model......Page 510 10.4.2 Affine camera model and the perspective projection......Page 512 10.4.3 Parameters of the affine camera model......Page 513 10.5 Weak perspective model......Page 514 10.6 Example of camera models......Page 516 10.7 Discussion......Page 526 10.8 References......Page 527 11.1 The least squares criterion......Page 528 11.2 Curve fitting by least squares......Page 530 12.1 Principal components analysis......Page 533 12.3 Covariance......Page 534 12.4 Covariance matrix......Page 537 12.5 Data transformation......Page 538 12.6 Inverse transformation......Page 539 12.7 Eigenproblem......Page 540 12.9 PCA method summary......Page 541 12.10 Example......Page 542 12.11 References......Page 548 13 Appendix 4: Color images......Page 549 13.2 Tristimulus theory......Page 550 13.3.1 The colorimetric equation......Page 552 13.3.2 Luminosity function......Page 553 13.3.3.1 CIE RGB color model: Wright–Guild data......Page 555 13.3.3.2 CIE RGB color matching functions......Page 556 13.3.3.3 CIE RGB chromaticity diagram and chromaticity coordinates......Page 559 13.3.3.4 CIE XYZ color model......Page 561 13.3.3.5 CIE XYZ color matching functions......Page 567 13.3.3.6 XYZ chromaticity diagram......Page 569 13.3.4 Uniform color spaces: CIE LUV and CIE LAB......Page 570 13.3.5.1 RGB and CMY......Page 576 13.3.5.2 Transformation between RGB color models......Page 578 13.3.5.3 Transformation between RGB and CMY color models......Page 581 13.3.6 Luminance and chrominance color models: YUV, YIQ, and YCbCr......Page 583 13.3.6.1 Luminance and gamma correction......Page 585 13.3.6.2 Chrominance......Page 587 13.3.6.3 Transformations between YUV, YIQ, and RGB color models......Page 588 13.3.6.4 Color model for component video: YPbPr......Page 589 13.3.6.5 Color model for digital video: YCbCr......Page 590 13.3.7 Perceptual color models: HSV and HLS......Page 591 13.3.7.1 The hexagonal model: HSV......Page 593 13.3.7.2 The triangular model: HSI......Page 598 13.3.8 More color models......Page 607 13.4 References......Page 608 Index......Page 609