
Handbook of Mathematical Models in Computer Vision
By: Nikos Paragios (Editor), Yunmei Chen (Editor), Olivier D. Faugeras (Editor)
Hardcover | 31 October 2005
At a Glance
640 Pages
24.77 x 16.51 x 3.81
Hardcover
$169.00
or 4 interest-free payments of $42.25 with
 orÂShips in 5 to 7 business days
Industry Reviews
From the reviews:
"The focus of the book is on mathematical methods that both model and reproduce human visual abilities. ... This book is a must-have for those interested in the full breadth of research done in the biological & computer vision community. As a bonus, the chapters can also be used in a seminar-based, advanced undergraduate course in mathematical based computer vision. " (Arjan Kuijper, IAPR Newsletter, October, 2006)
"Computational visual perception can be defined as the discipline of enabling computers to identify features in image data. ... I found this book to be detailed and comprehensive enough to be well worth the time spent on it. Citations linking the text to the relevant literature are profusely sprinkled throughout the text, and a very extensive bibliography is included ... . the production qualities are excellent. ... it should be a useful reference text for researchers or practitioners in this field." (R. M. Malyankar, Computing Reviews, January, 2006)
"The editors of this important compendium view their task as a contribution to modeling and simulating human vision by machine. ... The editors should be congratulated for bringing together high-level researchers to contribute chapters on cutting-edge technologies based on mathematical modeling. This compendium is a solid contribution to the recent literature combining the theories and applications of mathematical modeling to the domain of computer vision." (R. Goldberg, Computing Reviews, June, 2006)
| Preface | p. xix |
| List of Contributors | p. xxiii |
| Image Reconstruction | p. 1 |
| Diffusion Filters and Wavelets: What Can They Learn from Each Other? | p. 3 |
| Introduction | p. 3 |
| Basic Methods | p. 4 |
| Relations for Space-Discrete Diffusion | p. 6 |
| Relations for Fully Discrete Diffusion | p. 9 |
| Wavelets with Higher Vanishing Moments | p. 13 |
| Summary | p. 16 |
| Total Variation Image Restoration: Overview and Recent Developments | p. 17 |
| Introduction | p. 17 |
| Properties and Extensions | p. 19 |
| Caveats | p. 21 |
| Variants | p. 22 |
| Further Applications to Image Reconstruction | p. 26 |
| Numerical Methods | p. 29 |
| PDE-Based Image and Surface Inpainting | p. 33 |
| Introduction | p. 33 |
| Inpainting by Propagation of Information | p. 36 |
| Variational Models for Filling-In | p. 42 |
| Surface Reconstruction: The Laplace and the Absolute Minimizing Lipschitz Extension Interpolation | p. 52 |
| Dealing with texture | p. 55 |
| Other Approaches | p. 58 |
| Concluding Remarks | p. 60 |
| Appendix | p. 60 |
| Acknowledgments | p. 61 |
| Boundary Extraction, Segmentation and Grouping | p. 63 |
| Levelings: Theory and Practice | p. 65 |
| Introduction | p. 65 |
| Binary connected operators | p. 66 |
| Flat grey-tone connected operators | p. 67 |
| Extended connected operators | p. 68 |
| Levelings for image simplification | p. 71 |
| Conclusion | p. 77 |
| Graph Cuts in Vision and Graphics: Theories and Applications | p. 79 |
| Introduction | p. 79 |
| Graph Cuts Basics | p. 80 |
| Graph Cuts for Binary Optimization | p. 82 |
| Graph Cuts as Hypersurfaces | p. 84 |
| Generalizing Graph Cuts for Multi-Label Problems | p. 92 |
| Minimal Paths and Fast Marching Methods for Image Analysis | p. 97 |
| Introduction | p. 97 |
| Minimal Paths | p. 98 |
| Minimal paths from a set of endpoints p[subscript k] | p. 105 |
| Multiple minimal paths between regions R[subscript k] | p. 107 |
| Segmentation by Fast Marching | p. 108 |
| Centered Minimal Paths and virtual endoscopy | p. 110 |
| Conclusion | p. 111 |
| Integrating Shape and Texture in Deformable Models: from Hybrid Methods to Metamorphs | p. 113 |
| Introduction | p. 113 |
| Hybrid Segmentation Method | p. 116 |
| Metamorphs: Deformable Shape and Texture Models | p. 120 |
| Conclusions | p. 128 |
| Variational Segmentation with Shape Priors | p. 131 |
| Introduction | p. 131 |
| Shape Representation | p. 133 |
| Learning Shape Statistics | p. 136 |
| Variational Segmentation and Shape Priors | p. 139 |
| Conclusion and Further Work | p. 142 |
| Curve Propagation, Level Set Methods and Grouping | p. 145 |
| Introduction | p. 145 |
| On the Propagation of Curves | p. 146 |
| Data-driven Segmentation | p. 151 |
| Prior Knowledge | p. 154 |
| Discussion | p. 159 |
| On a Stochastic Model of Geometric Snakes | p. 161 |
| Introduction | p. 161 |
| Overview of Geodesic Snake Models | p. 163 |
| Birth and Death Zero Range Particle Systems | p. 163 |
| Poisson System Simulation | p. 164 |
| Choosing a Random Event | p. 166 |
| Similarity Invariant Flows | p. 168 |
| Stochastic Snakes | p. 171 |
| Experimental Results | p. 173 |
| Conclusions and Future Research | p. 174 |
| Shape Modeling & Registration | p. 175 |
| Invariant Processing and Occlusion Resistant Recognition of Planar Shapes | p. 177 |
| Introduction | p. 177 |
| Invariant Point Locations and Displacements | p. 178 |
| Invariant Boundary Signatures for Recognition under Partial Occlusions | p. 182 |
| Invariant Processing of Planar Shapes | p. 184 |
| Concluding Remarks | p. 188 |
| Planar Shape Analysis and Its Applications in Image-Based Inferences | p. 189 |
| Introduction | p. 189 |
| A Framework for Planar Shape Analysis | p. 191 |
| Clustering of Shapes | p. 194 |
| Interpolation of Shapes in Echocardiographic Image-Sequences | p. 196 |
| Study of Human Silhouettes in Infrared Images | p. 200 |
| Summary & Discussion | p. 202 |
| Diffeomorphic Point Matching | p. 205 |
| Introduction | p. 205 |
| Diffeomorphic Landmark Matching | p. 206 |
| Diffeomorphic Point Shape Matching | p. 214 |
| Discussion | p. 219 |
| Uncertainty-Driven, Point-Based Image Registration | p. 221 |
| Introduction | p. 221 |
| Objective Function, ICP and Normal Distances | p. 223 |
| Parameter Estimates and Covariance Matrices | p. 226 |
| Stable Sampling of ICP Constraints | p. 228 |
| Dual-Bootstrap ICP | p. 230 |
| Discussion and Conclusion | p. 234 |
| Motion Analysis, Optical Flow & Tracking | p. 237 |
| Optical Flow Estimation | p. 239 |
| Introduction | p. 239 |
| Basic Gradient-Based Estimation | p. 240 |
| Iterative Optical Flow Estimation | p. 243 |
| Robust Motion Estimation | p. 246 |
| Motion Models | p. 247 |
| Global Smoothing | p. 249 |
| Conservation Assumptions | p. 250 |
| Probabilistic Formulations | p. 252 |
| Layered Motion | p. 253 |
| Conclusions | p. 256 |
| From Bayes to PDEs in Image Warping | p. 259 |
| Motivation and problem statement | p. 259 |
| Admissible warps | p. 260 |
| Bayesian formulation of warp estimation | p. 262 |
| Likelihood: Matching criteria | p. 264 |
| Prior: Smoothness criteria | p. 266 |
| Warp time and computing time | p. 269 |
| From fluid registration to diffeomorphic minimizers | p. 270 |
| Discussion and open problems | p. 271 |
| Image Alignment and Stitching | p. 273 |
| Introduction | p. 273 |
| Motion models | p. 274 |
| Direct and feature-based alignment | p. 277 |
| Global registration | p. 283 |
| Choosing a compositing surface | p. 286 |
| Seam selection and pixel blending | p. 287 |
| Extensions and open issues | p. 291 |
| Visual Tracking: A Short Research Roadmap | p. 293 |
| Introduction | p. 293 |
| Simple appearance models | p. 294 |
| Active contours | p. 296 |
| Spatio-temporal filtering | p. 301 |
| Further topics | p. 306 |
| Shape Gradient for Image and Video Segmentation | p. 309 |
| Introduction | p. 309 |
| Problem Statement | p. 310 |
| From shape derivation tools towards region-based active contours models | p. 312 |
| Segmentation using Statistical Region-dependent descriptors | p. 317 |
| Discussion | p. 322 |
| Model-Based Human Motion Capture | p. 325 |
| Introduction | p. 325 |
| Methods | p. 327 |
| Results | p. 334 |
| Discussion | p. 338 |
| Modeling Dynamic Scenes: An Overview of Dynamic Textures | p. 341 |
| Introduction | p. 341 |
| Representation of dynamic textures | p. 344 |
| Learning dynamic textures | p. 344 |
| Model validation | p. 347 |
| Recognition | p. 349 |
| Segmentation | p. 351 |
| Discussion | p. 355 |
| 3D from Images, Projective Geometry & Stereo Reconstruction | p. 357 |
| Differential Geometry from the Frenet Point of View: Boundary Detection, Stereo, Texture and Color | p. 359 |
| Introduction | p. 359 |
| Introduction to Frenet-Serret | p. 361 |
| Co-Circularity in R[superscript 2] x S[superscript 1] | p. 363 |
| Stereo: Inferring Frenet 3-Frames from 2-Frames | p. 365 |
| Covariant Derivatives, Oriented Textures, and Color | p. 367 |
| Discussion | p. 372 |
| Shape From Shading | p. 375 |
| Introduction | p. 375 |
| Mathematical formulation of the SFS problem | p. 377 |
| Mathematical study of the SFS problem | p. 379 |
| Numerical solutions by "Propagation and PDEs methods" | p. 382 |
| Examples of numerical results | p. 385 |
| Conclusion | p. 388 |
| 3D from Image Sequences: Calibration, Motion and Shape Recovery | p. 389 |
| Introduction | p. 389 |
| Relating images | p. 392 |
| Structure and motion recovery | p. 393 |
| Dense surface estimation | p. 398 |
| 3D surface reconstruction | p. 400 |
| Conclusion | p. 402 |
| Multi-view Reconstruction of Static and Dynamic Scenes | p. 405 |
| Introduction | p. 405 |
| Reconstruction of Static Scenes | p. 406 |
| Reconstruction of Dynamic Scenes | p. 416 |
| Sensor Planning | p. 419 |
| Conclusion | p. 421 |
| Graph Cut Algorithms for Binocular Stereo with Occlusions | p. 423 |
| Traditional stereo methods | p. 423 |
| Stereo with occlusions | p. 426 |
| Voxel labeling algorithm | p. 429 |
| Pixel labeling algorithm | p. 430 |
| Minimizing the energy | p. 431 |
| Experimental results | p. 432 |
| Conclusions | p. 434 |
| Modelling Non-Rigid Dynamic Scenes from Multi-View Image Sequences | p. 439 |
| Introduction | p. 439 |
| Previous Work | p. 440 |
| The Prediction Error as a New Metric for Stereovision and Scene Flow Estimation | p. 443 |
| Experimental Results | p. 448 |
| Conclusion and Future Work | p. 451 |
| Applications: Medical Image Analysis | p. 453 |
| Interactive Graph-Based Segmentation Methods in Cardiovascular Imaging | p. 455 |
| Introduction | p. 455 |
| Characteristic Behaviors of the Algorithms | p. 456 |
| Applications on CT Cardiovascular data | p. 459 |
| Conclusions | p. 469 |
| 3D Active Shape and Appearance Models in Cardiac Image Analysis | p. 471 |
| Introduction | p. 471 |
| Methods | p. 475 |
| Discussion and Conclusion | p. 484 |
| Characterization of Diffusion Anisotropy in DWI | p. 487 |
| Introduction | p. 487 |
| Estimation of PDF | p. 489 |
| Estimation of ADC profiles | p. 493 |
| Conclusion | p. 499 |
| Segmentation of Diffusion Tensor Images | p. 503 |
| Introduction | p. 503 |
| K-means for DTI segmentation | p. 505 |
| Boundary-based active contours for DTI segmentation | p. 505 |
| Region-based active contour for DTI segmentation | p. 507 |
| Conclusion | p. 514 |
| Variational Approaches to the Estimation, Regularization and Segmentation of Diffusion Tensor Images | p. 517 |
| Introduction | p. 517 |
| Estimation of Diffusion Tensor Images | p. 518 |
| Regularization of Diffusion Tensor Images | p. 520 |
| Segmentation of Diffusion Tensor Images | p. 522 |
| Conclusion | p. 530 |
| An Introduction to Statistical Methods of Medical Image Registration | p. 531 |
| Introduction | p. 531 |
| The Similarity Measures | p. 532 |
| Conclusion | p. 541 |
| Bibliography | p. 543 |
| Bibliography | p. 543 |
| Table of Contents provided by Ingram. All Rights Reserved. |
ISBN: 9780387263717
ISBN-10: 0387263713
Published: 31st October 2005
Format: Hardcover
Language: English
Number of Pages: 640
Audience: Professional and Scholarly
Publisher: Springer Nature B.V.
Country of Publication: US
Dimensions (cm): 24.77 x 16.51 x 3.81
Weight (kg): 1.23
Shipping
| Standard Shipping | Express Shipping | |
|---|---|---|
| Metro postcodes: | $9.99 | $14.95 |
| Regional postcodes: | $9.99 | $14.95 |
| Rural postcodes: | $9.99 | $14.95 |
Orders over $79.00 qualify for free shipping.
How to return your order
At Booktopia, we offer hassle-free returns in accordance with our returns policy. If you wish to return an item, please get in touch with Booktopia Customer Care.
Additional postage charges may be applicable.
Defective items
If there is a problem with any of the items received for your order then the Booktopia Customer Care team is ready to assist you.
For more info please visit our Help Centre.
You Can Find This Book In
This product is categorised by
- Non-FictionComputing & I.T.Computer ScienceArtificial IntelligenceComputer Vision
- Non-FictionComputing & I.T.Graphical & Digital Media Applications3D Graphics & Modelling
- Non-FictionMathematicsApplied MathematicsMathematical Modelling
- Non-FictionComputing & I.T.Digital Lifestyle & Online World: Consumer & User GuidesInternet Guides & Online Services

























