Aja-Fernandez S., Luis Garcıa R., Tao D., Li X. Tensors in Image Processing and Computer Vision
размером 32,98 МБ
Добавлен пользователем Shushimora, дата добавления неизвестна
Издательство Springer, 2009, -466 pp.Over the past few years, tensor processing tools have become more and more popular in the fields of computer vision and image processing, and tensor-valued image modalities have also been more commonly employed, with the remarkable example of Diffusion Tensor Magnetic Resonance Imaging. However, tensor applications and tensor processing tools arise from very different areas. This can prevent important advances from rapidly spreading over the scientific community. Even though novel discoveries can greatly benefit many heterogeneous fields such as medical image processing or multilinear analysis, these advances are too often kept within the areas of knowledge where they were first employed. Given this fact, a compilation of some of the most recent advances in tensor processing can be a valuable tool for the scientific community, thus providing a useful reference state of the artfor tensor processing applications as well as a general insight on the areas where tensor processing is being successfully applied. The idea behind this book started after the Tensor Workshop held at the IEEE Computer Society Conference on Computer Vision and Pattern Recognition held in Anchorage, Alaska, in June 2008. This workshop gathered experts from different fields working on tensor processing, and some of the ideas presented there were further developed toghether with the results of the Tensor Workshop held earlier in Gran Canaria (Spain) in November 2006, which was sponsored by the SIMILAR Network of Excellence of the European 6th Framework Programme. As this book comprises theoretical advances and applications regarding very heterogeneous areas of image processing and computer vision, it has been organized into five parts, which are nevertheless preceeded by an introductory chapter about the different applications of the use of tensors in signal processing. Part I is devoted to the use of tensors and tensor field processing in general. The processing tools described in these chapters can be applied in a number of different applications. In Part II, two tensor techniques for image processing are presented. Later, Part III focuses on the use of tensors in computer vision applications, such as camera models or multilinear applications. As medical imaging is one of the areas that has taken more advantage of the advances of tensor processing, Part IV is dedicated to this issue, collecting applications from Diffusion Tensor Magnetic Resonance Imaging to strain tensor estimation in cardiac analysis or elastography imaging. Finally, Part V is devoted to storage, visualization and interfaces with tensors, an issue of considerable importance since this new data modality presents particularities that require new approaches to these otherwise traditional problems. The preparation of this book has been an arduous and difficult task. We would like to thank all the authors for their great effort and dedication in preparing their contributions. Also, all the reviewers, and specially the members of the editorial boards of the Tensor Workshops at CVPR’08 and in Gran Canaria in 2006, deserve our utmost gratitude. Thanks a lot to all of them.A Review of Tensors and Tensor Signal Processing Part I Tensors and Tensor Field Processing Segmentation of Tensor Fields: Recent Advances and Perspectives A Variational Approach to the Registration of Tensor-Valued Images Quality Assessment of Tensor Images Algorithms for Nonnegative Tensor Factorization PDE-based Morphology for Matrix Fields: Numerical Solution Schemes Part II Tensors in Image Processing Spherical Tensor Calculus for Local Adaptive Filtering On Geometric Transformations of Local Structure Tensors Part III Tensors in Computer Vision Multi-View Matching Tensors from Lines for General Camera Models Binocular Full-Body Pose Recognition and Orientation Inference Using Multilinear Analysis Applications of Multiview Tensors in Higher Dimensions Constraints for the Trifocal Tensor Part IV Diffusion Tensor Imaging and Medical Applications Review of Techniques for Registration of Diffusion Tensor Imaging Practical and Intuitive Basis for Tensor Field Processing with Invariant Gradients and Rotation Tangents From Second to Higher Order Tensors in Diffusion-MRI DT-MRI Connectivity and/or Tractography?: Two New Algorithms Strain Rate Tensor Estimation in Cine Cardiac MRI Based on Elastic Image Registration Strain Tensor Elastography: 2D and 3D Visualizations Part V Storage, Visualization and Interfaces Similar Tensor Arrays – A Framework for Storage of Tensor Array Data User Interfaces to Interact with Tensor Fields T-flash: Tensor Visualization in Medical Studio
Чтобы скачать этот файл зарегистрируйтесь и/или войдите на сайт используя форму сверху.
Packt Publishing, 2012 (December). - 340 pages. На англ. языке.
Step-by-step tutorials to solve common real-world computer vision problems for desktop or mobile, from augmented reality and number plate recognition to face recognition and 3D head tracking
Allows anyone with basic OpenCV experience to rapidly obtain skills in many computer vision topics, for...
Springer, 2006. — 738 p. — ISBN 0387310738, 978-0387310732. Pattern recognition has its origins in engineering, whereas machine learning grew out of computer science. However, these activities can be viewed as two facets of the same field, and together they have undergone substantial development over the past ten years. In particular, Bayesian methods have grown from a specialist...
Cambridge University Press, 2012. — 396 p. — ISBN: 978-1107096394.
As one of the most comprehensive machine learning texts around, this book does justice to the field's incredible richness, but without losing sight of the unifying principles. Peter Flach's clear, example-based approach begins by discussing how a spam filter works, which gives an immediate introduction to...
Massachusetts Institute of Technology, 2012. — 1067 p.
ISBN: 0262018020, 978-0262018029.
Today's Web-enabled deluge of electronic data calls for automated methods of data analysis. Machine learning provides these, developing methods that can automatically detect patterns in data and then use the uncovered patterns to predict future data. This textbook offers a comprehensive...