This volume contains the proceedings from two closely related workshops: Computational Diffusion MRI (CDMRI 13) and Mathematical Methods from Brain Connectivity (MMBC 13), held under the auspices of the 16th International Conference on Medical Image Computing and Computer Assisted Intervention, which took place in Nagoya, Japan, September 2013.

Inside, readers will find contributions ranging from mathematical foundations and novel methods for the validation of inferring large-scale connectivity from neuroimaging data to the statistical analysis of the data, accelerated methods for data acquisition, and the most recent developments on mathematical diffusion modeling.

This volume offers a valuable starting point for anyone interested in learning computational diffusion MRI and mathematical methods for brain connectivity as well as offers new perspectives and insights on current research challenges for those currently in the field. It will be of interest to researchers and practitioners in computer science, MR physics, and applied mathematics.

"

Tensor signal processing is an emerging field with important applications to computer vision and image processing.

This book presents the state of the art in this new branch of signal processing, offering a great deal of research and discussions by leading experts in the area. The wide-ranging volume offers an overview into cutting-edge research into the newest tensor processing techniques and their application to different domains related to computer vision and image processing.

This comprehensive text will prove to be an invaluable reference and resource for researchers, practitioners and advanced students working in the area of computer vision and image processing.

A principal aim of computer graphics is to generate images that look as real as photographs. Realistic computer graphics imagery has however proven to be quite challenging to produce, since the appearance of materials arises from complicated physical processes that are difficult to analytically model and simulate, and image-based modeling of real material samples is often impractical due to the high-dimensional space of appearance data that needs to be acquired.

This book presents a general framework based on the inherent coherency in the appearance data of materials to make image-based appearance modeling more tractable. We observe that this coherence manifests itself as low-dimensional structure in the appearance data, and by identifying this structure we can take advantage of it to simplify the major processes in the appearance modeling pipeline. This framework consists of two key components, namely the coherence structure and the accompanying reconstruction method to fully recover the low-dimensional appearance data from sparse measurements. Our investigation of appearance coherency has led to three major forms of low-dimensional coherence structure and three types of coherency-based reconstruction upon which our framework is built.

This coherence-based approach can be comprehensively applied to all the major elements of image-based appearance modeling, from data acquisition of real material samples to user-assisted modeling from a photograph, from synthesis of volumes to editing of material properties, and from efficient rendering algorithms to physical fabrication of objects. In this book we present several techniques built on this coherency framework to handle various appearance modeling tasks both for surface reflections and subsurface scattering, the two primary physical components that generate material appearance. We believe that coherency-based appearance modeling will make it easier and more feasible for practitioners to bring computer graphics imagery to life.

This book is aimed towards readers with an interest in computer graphics. In particular, researchers, practitioners and students will benefit from this book by learning about the underlying coherence in appearance structure and how it can be utilized to improve appearance modeling. The specific techniques presented in our manuscript can be of value to anyone who wishes to elevate the realism of their computer graphics imagery. For understanding this book, an elementary background in computer graphics is assumed, such as from an introductory college course or from practical experience with computer graphics.

The book written by Dr. Radu B. Rusu presents a detailed description of 3D Semantic Mapping in the context of mobile robot manipulation. As autonomous robotic platforms get more sophisticated manipulation capabilities, they also need more expressive and comprehensive environment models that include the objects present in the world, together with their position, form, and other semantic aspects, as well as interpretations of these objects with respect to the robot tasks.

The book proposes novel 3D feature representations called Point Feature Histograms (PFH), as well as a frameworks for the acquisition and processing of Semantic 3D Object Maps with contributions to robust registration, fast segmentation into regions, and reliable object detection, categorization, and reconstruction. These contributions have been fully implemented and empirically evaluated on different robotic systems, and have been the original kernel to the widely successful open-source project the Point Cloud Library (PCL) -- see http: //pointclouds.org.

Image processing algorithms based on the mammalian visual cortex are powerful tools for extraction information and manipulating images. This book reviews the neural theory and translates them into digital models. Applications are given in areas of image recognition, foveation, image fusion and information extraction. The third edition reflects renewed international interest in pulse image processing with updated sections presenting several newly developed applications. This edition also introduces a suite of Python scripts that assist readers in replicating results presented in the text and to further develop their own applications.

This book provides comprehensive coverage of the latest trends/advances in subjective and objective quality evaluation for traditional visual signals, such as 2D images and video, as well as the most recent challenges for the field of multimedia quality assessment and processing, such as mobile video and social media. Readers will learn how to ensure the highest storage/delivery/ transmission quality of visual content (including image, video, graphics, animation, etc.) from the server to the consumer, under resource constraints, such as computation, bandwidth, storage space, battery life, etc.

This reference provides an in-depth discussion of the theory and application of lapped transforms (LTs). It explains how LTs can lead to a better complexity/performance trade-off than other transforms or filter bands used in signal processing. The text addresses the increased use LTs, especially with HDTV and how they may become the standard for high-quality audio coding.

The goal of this book is to present the topic of discrete calculus to scientists and - gineers and to show how the theory can be applied to solving a wide variety of re- world problems. We feel that discrete calculus allows us to unify many approaches to data analysis and content extraction while being accessible enough to be widely applied in many ?elds and disciplines. This project initially began as a tutorial on discrete calculus and its applications, and we hope that this work can provide an introduction to discrete calculus and demonstrate its effectiveness in many problem domains. This book bene?ted enormously from the friends and colleagues who provided software, data, and their time in reading the manuscript. In particular, for software we would like to thank Sebastien Bougleux for help with total variation code for an arbitrary graph and Camille Couprie for powerwatershed code. For use of their data, we wish to thank Jason Bohland, James Fowler, David Gleich, and Robert S- ner. For comments on the manuscript we would like to thank Christopher Alvino, Mukund Balasubramanian, Jason Bohland, Sebastien Bougleux, Gaelle Desbordes, Mathieu Desbrun, Noha El-Zehiry, Gareth Funka-Lea, David Gleich, Oliver Hinds, Anil Hirani, Hiroshi Ishikawa, Robert Kotiuga, Elliot Saltzman, Dheeraj Singaraju, Ganesh Sundaramoorthi and Enzo Tonti. We thank Eric Schwartz for all his help and support over the years. We would like to thank Wayne Wheeler, Simon Rees, and Catherine Brett at Springer for their enthusiasm and for initially proposing this project.

This text covers state-of-the-art color image and video enhancement techniques. The book examines the multivariate nature of color image/video data as it pertains to contrast enhancement, color correction (equalization, harmonization, normalization, balancing, constancy, etc.), noise removal and smoothing. This book also discusses color and contrast enhancement in vision sensors and applications of image and video enhancement.

This book presents the use of efficient Evolutionary Computation (EC) algorithms for solving diverse real-world image processing and pattern recognition problems. It provides an overview of the different aspects of evolutionary methods in order to enable the reader in reaching a global understanding of the field and, in conducting studies on specific evolutionary techniques that are related to applications in image processing and pattern recognition. It explains the basic ideas of the proposed applications in a way that can also be understood by readers outside of the field. Image processing and pattern recognition practitioners who are not evolutionary computation researchers will appreciate the discussed techniques beyond simple theoretical tools since they have been adapted to solve significant problems that commonly arise on such areas. On the other hand, members of the evolutionary computation community can learn the way in which image processing and pattern recognition problems can be translated into an optimization task. The book has been structured so that each chapter can be read independently from the others. It can serve as reference book for students and researchers with basic knowledge in image processing and EC methods.

This book presents how multimedia data analysis, information retrieval and indexing are central for comprehensive, personalized, adaptive quality care and the prolongation of independent living at home. With sophisticated technologies in monitoring, diagnosis, and treatment, multimodal data plays an increasingly central role in healthcare. Experts in computer vision, image processing, medical imaging, biomedical engineering, medical informatics, physical education and motor control, visual learning, nursing and human sciences, information retrieval, content based image retrieval, eHealth, information fusion, multimedia communications and human computer interaction come together to provide a thorough overview of multimedia analysis in medicine and daily life.

This unique text/reference presents a fresh look at nonlinear processing through nonlinear eigenvalue analysis, highlighting how one-homogeneous convex functionals can induce nonlinear operators that can be analyzed within an eigenvalue framework. The text opens with an introduction to the mathematical background, together with a summary of classical variational algorithms for vision. This is followed by a focus on the foundations and applications of the new multi-scale representation based on non-linear eigenproblems. The book then concludes with a discussion of new numerical techniques for finding nonlinear eigenfunctions, and promising research directions beyond the convex case. Topics and features: introduces the classical Fourier transform and its associated operator and energy, and asks how these concepts can be generalized in the nonlinear case; reviews the basic mathematical notion, briefly outlining the use of variational and flow-based methods to solve image-processing and computer vision algorithms; describes the properties of the total variation (TV) functional, and how the concept of nonlinear eigenfunctions relate to convex functionals; provides a spectral framework for one-homogeneous functionals, and applies this framework for denoising, texture processing and image fusion; proposes novel ways to solve the nonlinear eigenvalue problem using special flows that converge to eigenfunctions; examines graph-based and nonlocal methods, for which a TV eigenvalue analysis gives rise to strong segmentation, clustering and classification algorithms; presents an approach to generalizing the nonlinear spectral concept beyond the convex case, based on pixel decay analysis; discusses relations to other branches of image processing, such as wavelets and dictionary based methods. This original work offers fascinating new insights into established signal processing techniques, integrating deep mathematical concepts from a range of different fields, which will be of great interest to all researchers involved with image processing and computer vision applications, as well as computations for more general scientific problems.

Developing algorithms for multi-dimensional Fourier transforms, this book presents results that yield highly efficient code on a variety of vector and parallel computers. By emphasising the unified basis for the many approaches to both one-dimensional and multidimensional Fourier transforms, this book not only clarifies the fundamental similarities, but also shows how to exploit the differences in optimising implementations. It will thus be of great interest not only to applied mathematicians and computer scientists, but also to seismologists, high-energy physicists, crystallographers, and electrical engineers working on signal and image processing.

This is an edited volume, written by well-recognized international researchers with extended chapter style versions of the best papers presented at the SITIS 2006 International Conference. This book presents the state-of-the-art and recent research results on the application of advanced signal processing techniques for improving the value of image and video data. It introduces new results on video coding on time-honored topic of securing image information. The book is designed for a professional audience composed of practitioners and researchers in industry. This book is also suitable for advanced-level students in computer science.

Video segmentation has become one of the core areas in visual signal processing research. The objective of Video Segmentation and Its Applications is to present the latest advances in video segmentation and analysis techniques while covering the theoretical approaches, real applications and methods being developed in the computer vision and video analysis community. The book will also provide researchers and practitioners a comprehensive understanding of state-of-the-art of video segmentation techniques and a resource for potential applications and successful practice.

Aims and Scope This book is both an introductory textbook and a research monograph on modeling the statistical structure of natural images. In very simple terms, "natural images" are photographs of the typical environment where we live. In this book, their statistical structure is described using a number of statistical models whose parameters are estimated from image samples. Our main motivation for exploring natural image statistics is computational m- eling of biological visual systems. A theoretical framework which is gaining more and more support considers the properties of the visual system to be re?ections of the statistical structure of natural images because of evolutionary adaptation processes. Another motivation for natural image statistics research is in computer science and engineering, where it helps in development of better image processing and computer vision methods. While research on natural image statistics has been growing rapidly since the mid-1990s, no attempt has been made to cover the ?eld in a single book, providing a uni?ed view of the different models and approaches. This book attempts to do just that. Furthermore, our aim is to provide an accessible introduction to the ?eld for students in related disciplines.

This book presents the state-of-the-art in face detection and analysis. It outlines new research directions, including in particular psychology-based facial dynamics recognition, aimed at various applications such as behavior analysis, deception detection, and diagnosis of various psychological disorders. Topics of interest include face and facial landmark detection, face recognition, facial expression and emotion analysis, facial dynamics analysis, face classification, identification, and clustering, and gaze direction and head pose estimation, as well as applications of face analysis.

This book examines the context, motivation and current status of biometric systems based on the palmprint, with a specific focus on touchless and less-constrained systems. It covers new technologies in this rapidly evolving field and is one of the first comprehensive books on palmprint recognition systems. It discusses the research literature and the most relevant industrial applications of palmprint biometrics, including the low-cost solutions based on webcams. The steps of biometric recognition are described in detail, including acquisition setups, algorithms, and evaluation procedures. Constraints and limitations of current palmprint recognition systems are analyzed and discussed. The authors also introduce innovative methods for touchless and less-constrained palmprint recognition, with the aim to make palmprint biometrics easier to use in practical, daily-life applications, and overcome the typical constraints and limitations described. Touchless Palmprint Recognition Systems targets professionals and researchers working in biometrics, image processing and three-dimensional reconstruction. Advanced-level students studying biometrics and computer science will also find this material valuable as a secondary text book or reference.

This book presents advanced methodologies in two areas related to electroencephalogram (EEG) signals: detection of epileptic seizures and identification of mental states in brain computer interface (BCI) systems. The proposed methods enable the extraction of this vital information from EEG signals in order to accurately detect abnormalities revealed by the EEG. New methods will relieve the time-consuming and error-prone practices that are currently in use. Common signal processing methodologies include wavelet transformation and Fourier transformation, but these methods are not capable of managing the size of EEG data. Addressing the issue, this book examines new EEG signal analysis approaches with a combination of statistical techniques (e.g. random sampling, optimum allocation) and machine learning methods. The developed methods provide better results than the existing methods. The book also offers applications of the developed methodologies that have been tested on several real-time benchmark databases. This book concludes with thoughts on the future of the field and anticipated research challenges. It gives new direction to the field of analysis and classification of EEG signals through these more efficient methodologies. Researchers and experts will benefit from its suggested improvements to the current computer-aided based diagnostic systems for the precise analysis and management of EEG signals.

A wide variety of processes occur on multiple scales, either naturally or as a consequence of measurement. This book contains methodology for the analysis of data that arise from such multiscale processes. The book brings together a number of recent developments and makes them accessible to a wider audience. Taking a Bayesian approach allows for full accounting of uncertainty, and also addresses the delicate issue of uncertainty at multiple scales. The Bayesian approach also facilitates the use of knowledge from prior experience or data, and these methods can handle different amounts of prior knowledge at different scales, as often occurs in practice.

The book is aimed at statisticians, applied mathematicians, and engineers working on problems dealing with multiscale processes in time and/or space, such as in engineering, finance, and environmetrics. The book will also be of interest to those working on multiscale computation research. The main prerequisites are knowledge of Bayesian statistics and basic Markov chain Monte Carlo methods. A number of real-world examples are thoroughly analyzed in order to demonstrate the methods and to assist the readers in applying these methods to their own work. To further assist readers, the authors are making source code (for R) available for many of the basic methods discussed herein.

This book summarizes the organized competitions held during the first NIPS competition track. It provides both theory and applications of hot topics in machine learning, such as adversarial learning, conversational intelligence, and deep reinforcement learning. Rigorous competition evaluation was based on the quality of data, problem interest and impact, promoting the design of new models, and a proper schedule and management procedure. This book contains the chapters from organizers on competition design and from top-ranked participants on their proposed solutions for the five accepted competitions: The Conversational Intelligence Challenge, Classifying Clinically Actionable Genetic Mutations, Learning to Run, Human-Computer Question Answering Competition, and Adversarial Attacks and Defenses.

Hyperspectral Image Fusion is the first text dedicated to the fusion techniques for such a huge volume of data consisting of a very large number of images. This monograph brings out recent advances in the research in the area of visualization of hyperspectral data. It provides a set of pixel-based fusion techniques, each of which is based on a different framework and has its own advantages and disadvantages. The techniques are presented with complete details so that practitioners can easily implement them. It is also demonstrated how one can select only a few specific bands to speed up the process of fusion by exploiting spatial correlation within successive bands of the hyperspectral data. While the techniques for fusion of hyperspectral images are being developed, it is also important to establish a framework for objective assessment of such techniques. This monograph has a dedicated chapter describing various fusion performance measures that are applicable to hyperspectral image fusion. This monograph also presents a notion of consistency of a fusion technique which can be used to verify the suitability and applicability of a technique for fusion of a very large number of images. This book will be a highly useful resource to the students, researchers, academicians and practitioners in the specific area of hyperspectral image fusion, as well as generic image fusion.

This book presents a comprehensive treatise on Riemannian geometric computations and related statistical inferences in several computer vision problems. This edited volume includes chapter contributions from leading figures in the field of computer vision who are applying Riemannian geometric approaches in problems such as face recognition, activity recognition, object detection, biomedical image analysis, and structure-from-motion. Some of the mathematical entities that necessitate a geometric analysis include rotation matrices (e.g. in modeling camera motion), stick figures (e.g. for activity recognition), subspace comparisons (e.g. in face recognition), symmetric positive-definite matrices (e.g. in diffusion tensor imaging), and function-spaces (e.g. in studying shapes of closed contours).

This volume presents the results of the Neural Information Processing Systems Competition track at the 2018 NeurIPS conference. The competition follows the same format as the 2017 competition track for NIPS. Out of 21 submitted proposals, eight competition proposals were selected, spanning the area of Robotics, Health, Computer Vision, Natural Language Processing, Systems and Physics. Competitions have become an integral part of advancing state-of-the-art in artificial intelligence (AI). They exhibit one important difference to benchmarks: Competitions test a system end-to-end rather than evaluating only a single component; they assess the practicability of an algorithmic solution in addition to assessing feasibility. The eight run competitions aim at advancing the state of the art in deep reinforcement learning, adversarial learning, and auto machine learning, among others, including new applications for intelligent agents in gaming and conversational settings, energy physics, and prosthetics.

This book presents and develops new reinforcement learning methods that enable fast and robust learning on robots in real-time. Robots have the potential to solve many problems in society, because of their ability to work in dangerous places doing necessary jobs that no one wants or is able to do. One barrier to their widespread deployment is that they are mainly limited to tasks where it is possible to hand-program behaviors for every situation that may be encountered. For robots to meet their potential, they need methods that enable them to learn and adapt to novel situations that they were not programmed for. Reinforcement learning (RL) is a paradigm for learning sequential decision making processes and could solve the problems of learning and adaptation on robots. This book identifies four key challenges that must be addressed for an RL algorithm to be practical for robotic control tasks. These RL for Robotics Challenges are: 1) it must learn in very few samples; 2) it must learn in domains with continuous state features; 3) it must handle sensor and/or actuator delays; and 4) it should continually select actions in real time. This book focuses on addressing all four of these challenges. In particular, this book is focused on time-constrained domains where the first challenge is critically important. In these domains, the agent's lifetime is not long enough for it to explore the domains thoroughly, and it must learn in very few samples.