It has long been a dream to realize machines with flexible visual perception capability. Research on digital image processing by computers was initiated about 30 years ago, and since then a wide variety of image processing algorithms have been devised. Using such image processing algorithms and advanced hardware technologies, many practical ma chines with visual recognition capability have been implemented and are used in various fields: optical character readers and design chart readers in offices, position-sensing and inspection systems in factories, computer tomography and medical X-ray and microscope examination systems in hospitals, and so on. Although these machines are useful for specific tasks, their capabilities are limited. That is, they can analyze only simple images which are recorded under very carefully adjusted photographic conditions: objects to be recognized are isolated against a uniform background and under well-controlled artificial lighting. In the late 1970s, many image understanding systems were de veloped to study the automatic interpretation of complex natural scenes. They introduced artificial intelligence techniques to represent the knowl edge about scenes and to realize flexible control structures. The first author developed an automatic aerial photograph interpretation system based on the blackboard model (Naga1980). Although these systems could analyze fairly complex scenes, their capabilities were still limited; the types of recognizable objects were limited and various recognition vii viii Preface errors occurred due to noise and the imperfection of segmentation algorithms."

Shape Analysis and Retrieval of Multimedia Objects provides a comprehensive survey of the most advanced and powerful shape retrieval techniques used in practice today. In addition, this monograph addresses key methodological issues for evaluation of the shape retrieval methods. Shape Analysis and Retrieval of Multimedia Objects is designed to meet the needs of practitioners and researchers in industry, and graduate-level students in Computer Science.

This book constitutes the refereed proceedings of the 4th International Conference on Scale Space Methods and Variational Methods in Computer Vision, SSVM 2013, held in Schloss Seggau near Graz, Austria, in June 2013. The 42 revised full papers presented were carefully reviewed and selected 69 submissions. The papers are organized in topical sections on image denoising and restoration, image enhancement and texture synthesis, optical flow and 3D reconstruction, scale space and partial differential equations, image and shape analysis, and segmentation.

The world is full of objects, many of which are visible to us as surfaces. Examples are people, cars, machines, computers and bananas. Exceptions are such things as clouds and trees, which have a more detailed, fuzzy structure. Computer vision aims to detect and reconstruct features of surfaces from the images produced by cameras, in some ways mimicking the way in which humans reconstruct features of the world around them by using their eyes. This book describes how the 3D shape of surfaces can be recovered from image sequences of outlines. Cipolla and Giblin provide all the necessary background in differential geometry (assuming knowledge of elementary algebra and calculus) and in the analysis of visual motion, and emphasizes intuitive visual understanding of the geometric techniques with computer-generated illustrations. They also give a thorough introduction to the mathematical techniques and the details of the implementations, and apply the methods to data from real images.

Recently, much attention has been paid to image processing with multiresolution and hierarchical structures such as pyramids and trees. This volume deals with recursive pyramids, which combine the advantages of available multiresolution structures and which are convenient both for global and local image processing. Recursive pyramids are based on regular hierarchical (recursive) structures containing data on image fragments of different sizes. Such an image representation technique enables the effective manipulation of pictorial information as well as the development of special hardware or data structures. The major aspects of this book are two original mathematical models of greyscale and binary images represented by recursive structures. Image compression, transmission and processing are discussed using these models. A number of applications are presented, including optical character recognition, expert systems and special computer architecture for pictorial data processing. The majority of results are presented as algorithms applicable to discrete information fields of arbitrary dimensions (e.g. 2-D or 3-D images). The book is divided into six chapters: Chapter 1 provides a brief introduction. Chapter 2 then deals with recursive structures and their properties. Chapter 3 introduces pyramidal image models. Image coding and the progressive transmission of images with gradual refinement are discussed in Chapter 4. Chapters 5 and 6 are devoted to image processing with pyramidal-recursive structures and applications. The volume concludes with a comprehensive bibliography. For applied mathematicians and computer scientists whose work involves computer vision, information theory and other aspects of image representation techniques.

Image analysis is one of the most challenging areas in today's computer sci ence, and image technologies are used in a host of applications. This book concentrates on image textures and presents novel techniques for their sim ulation, retrieval, and segmentation using specific Gibbs random fields with multiple pairwise interaction between signals as probabilistic image models. These models and techniques were developed mainly during the previous five years (in relation to April 1999 when these words were written). While scanning these pages you may notice that, in spite of long equa tions, the mathematical background is extremely simple. I have tried to avoid complex abstract constructions and give explicit physical (to be spe cific, "image-based") explanations to all the mathematical notions involved. Therefore it is hoped that the book can be easily read both by professionals and graduate students in computer science and electrical engineering who take an interest in image analysis and synthesis. Perhaps, mathematicians studying applications of random fields may find here some less traditional, and thus controversial, views and techniques.

This book constitutes the thoroughly refereed post-conference proceedings of the 6th International ICST Conference on Mobile Multimedia Communications (MOBIMEDIA 2010) held in Lisbon, Portugal, in September 2010, which was accompanied by the First International Workshop on Cognitive Radio and Cooperative Strategies for POWER Saving (C2POWER 2010), the Workshop on Impact of Scalable Video Coding on Multimedia Provisioning (SVCVision 2010), and the First International Workshop on Energy-efficient and Reconfigurable Transceivers (EERT 2010). The 59 revised full papers presented were carefully reviewed and selected from numerous submissions and are organized in topical sections on advanced techniques for video transmission; multimedia distribution; modelling of wireless systems; cellular networks; mobility concepts for IMT-advances (MOBILIA); media independent handovers (MIH-4-MEDIA); and IP-based emergency applications and services for next generation networks (PEACE).

Human Face Recognition Using Third-Order Synthetic Neural Networks explores the viability of the application of High-order synthetic neural network technology to transformation-invariant recognition of complex visual patterns. High-order networks require little training data (hence, short training times) and have been used to perform transformation-invariant recognition of relatively simple visual patterns, achieving very high recognition rates. The successful results of these methods provided inspiration to address more practical problems which have grayscale as opposed to binary patterns (e.g., alphanumeric characters, aircraft silhouettes) and are also more complex in nature as opposed to purely edge-extracted images - human face recognition is such a problem. Human Face Recognition Using Third-Order Synthetic Neural Networks serves as an excellent reference for researchers and professionals working on applying neural network technology to the recognition of complex visual patterns.

Perceptual Organization for Artificial Vision Systems is an edited collection of invited contributions based on papers presented at The Workshop on Perceptual Organization in Computer Vision, held in Corfu, Greece, in September 1999. The theme of the workshop was 'Assessing the State of the Community and Charting New Research Directions.' Perceptual organization can be defined as the ability to impose structural regularity on sensory data, so as to group sensory primitives arising from a common underlying cause. This book explores new models, theories, and algorithms for perceptual organization. Perceptual Organization for Artificial Vision Systems includes contributions by the world's leading researchers in the field. It explores new models, theories, and algorithms for perceptual organization, as well as demonstrates the means for bringing research results and theoretical principles to fruition in the construction of computer vision systems. The focus of this collection is on the design of artificial vision systems. The chapters comprise contributions from researchers in both computer vision and human vision.

During the past few years, we have been witnessing the rapid growth of the ap plications of Interactive Digital Video, Multimedia Computing, Desktop Video Teleconferencing, Virtual Reality, and High Definition Television (HDTV). An other information revolution which is tied to Cyberspace is almost within reach. The information, data, text, graphics, video, sound, etc. , in the form of multi media, can be requested, accessed, distributed, and transmitted to potentially every household. This is changing and will continue to change the way of people doing business, functioning in the society, and entertaining. In the foreseeable future, many personalized, portable information terminals, which can be car ried while traveling, will provide the link to central computer network to allow information exchange including videos from a node to node, from a center to a node, or nodes. Facing this opportunity, the question is what are the major significant technical challenges that people have to solve to push the-state-of-the-art for the realiza tion of the above mentioned technology advancement? From our professional judgement We feel that one of the major technical challenges is in Video Data Compression. Video communications in the form of desktop teleconferencing, videophone, network video delivery on demand, even games, are going to be major media traveling in the information super highway, hopping from one node in the Cyberspace to the other.

The key contribution of the approach to x-ray mammographic image analysis developed in this monograph is a representation of the non-fatty compressed breast tissue that we show can be derived from a single mammogram. The importance of the representation, called hint, is that it removes all those changes in the image that are due only to the particular imaging conditions (for example, the film speed or exposure time), leaving just the non-fatty interesting' tissue. Normalising images in this way enables them to be enhanced and matched, and regions in them to be classified more reliably, because unnecessary, distracting variations have been eliminated. Part I of the monograph develops a model-based approach to x-ray mammography, Part II shows how it can be put to work successfully on a range of clinically-important tasks, while Part III develops a model and exploits it for contrast-enhanced MRI mammography. The final chapter points the way forward in a number of promising areas of research. Audience: This book has been written for a wide readership, including medical image analysts, medical physicists, radiologists, breast surgeons, and research students. The mathematics and algorithms have been relegated to boxes so that the book can be read and understood even if the mathematical detail is skipped. Large parts of the monograph will be of interest to clinicians generally and to patients.

Vision-based mobile robot guidance has proved difficult for classical machine vision methods because of the diversity and real-time constraints inherent in the task. This book describes a connectionist system called ALVINN (Autonomous Land Vehicle In a Neural Network) that overcomes these difficulties. ALVINN learns to guide mobile robots using the back-propagation training algorithm. Because of its ability to learn from example, ALVINN can adapt to new situations and therefore cope with the diversity of the autonomous navigation task. But real world problems like vision-based mobile robot guidance present a different set of challenges for the connectionist paradigm. Among them are: * how to develop a general representation from a limited amount of real training data; * how to understand the internal representations developed by artificial neural networks; * how to estimate the reliability of individual networks; * how to combine multiple networks trained for different situations into a single system; * how to combine connectionist perception with symbolic reasoning.Neural Network Perception for Mobile Robot Guidance presents novel solutions to each of these problems. Using these techniques, the ALVINN system can learn to control an autonomous van in under 5 minutes by watching a person drive. Once trained, individual ALVINN networks can drive in a variety of circumstances, including single-lane paved and unpaved roads, and multi-lane lined and unlined roads, at speeds of up to 55 miles per hour. The techniques also are shown to generalize to the task of controlling the precise foot placement of a walking robot.

This book constitutes the refereed proceedings of the 9th International Tbilisi Symposium on Logic, Language, and Computation, TbiLLC 2011, held in Kutaisi, Georgia, in September 2011. The book consists of summaries of 3 tutorials presented at the symposium together with 13 full papers that were carefully reviewed and selected from the submissions. The papers are organized in two sections, one on Language and one on Logic and Computation. The range of topics covered in the Language section includes natural language syntax, semantics, and pragmatics, frames in natural language semantics, linguistic typology, and discourse phenomena. The papers in the Logic and Computation section cover such topics as constructive, modal, algebraic, and philosophical logic, as well as logics for computer science applications.

This book constitutes the thoroughly refereed proceedings of the 2012 ICSOC Workshops consisting of 6 scientific satellite events, organized in 3 main tracks including workshop track (ASC, DISA. PAASC, SCEB, SeMaPS and WESOA 2012), PhD symposium track, demonstration track; held in conjunction with the 10th International Conference on Service-Oriented Computing (ICSOC), in Shanghai, China, November 2012. The 53 revised papers presents a wide range of topics that fall into the general area of service computing such as business process management, distributed systems, computer networks, wireless and mobile computing, grid computing, networking, service science, management science, and software engineering.

This book constitutes the thoroughly refereed post-conference proceedings of the 5th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2012, held in Vilamoura, Portugal, in February 2012. The 26 revised full papers presented together with one invited lecture were carefully reviewed and selected from a total of 522 submissions. The papers cover a wide range of topics and are organized in four general topical sections on biomedical electronics and devices; bioinformatics models, methods and algorithms; bio-inspired systems and signal processing; health informatics.

This book constitutes the refereed proceedings of the Chinese Conference on Image and Graphics Technologies and Applications, IGTA 2013, held in Beijing, China, in April 2013. The 40 papers and posters presented were carefully reviewed and selected from 89 submissions. The papers address issues such as the generation of new ideas, new approaches, new techniques, new applications and new evaluation in the field of image processing and graphics.

1. Introduction . 1 2. Areas and Angles . . 6 3. Tessellations and Symmetry 14 4. The Postulate of Closest Approach 28 5. The Coexistence of Rotocenters 36 6. A Diophantine Equation and its Solutions 46 7. Enantiomorphy. . . . . . . . 57 8. Symmetry Elements in the Plane 77 9. Pentagonal Tessellations . 89 10. Hexagonal Tessellations 101 11. Dirichlet Domain 106 12. Points and Regions 116 13. A Look at Infinity . 122 14. An Irrational Number 128 15. The Notation of Calculus 137 16. Integrals and Logarithms 142 17. Growth Functions . . . 149 18. Sigmoids and the Seventh-year Trifurcation, a Metaphor 159 19. Dynamic Symmetry and Fibonacci Numbers 167 20. The Golden Triangle 179 21. Quasi Symmetry 193 Appendix I: Exercise in Glide Symmetry . 205 Appendix II: Construction of Logarithmic Spiral . 207 Bibliography . 210 Index . . . . . . . . . . . . . . . . . . . . 225 Concepts and Images is the result of twenty years of teaching at Harvard's Department of Visual and Environmental Studies in the Carpenter Center for the Visual Arts, a department devoted to turning out students articulate in images much as a language department teaches reading and expressing one self in words. It is a response to our students' requests for a "handout" and to l our colleagues' inquiries about the courses: Visual and Environmental Studies 175 (Introduction to Design Science), YES 176 (Synergetics, the Structure of Ordered Space), Studio Arts 125a (Design Science Workshop, Two-Dimension al), Studio Arts 125b (Design Science Workshop, Three-Dimensional),2 as well as my freshman seminars on Structure in Science and Art."

Video Object Extraction and Representation: Theory and Applications is an essential reference for electrical engineers working in video; computer scientists researching or building multimedia databases; video system designers; students of video processing; video technicians; and designers working in the graphic arts. In the coming years, the explosion of computer technology will enable a new form of digital media. Along with broadband Internet access and MPEG standards, this new media requires a computational infrastructure to allow users to grab and manipulate content. The book reviews relevant technologies and standards for content-based processing and their interrelations. Within this overview, the book focuses upon two problems at the heart of the algorithmic/computational infrastructure: video object extraction, or how to automatically package raw visual information by content; and video object representation, or how to automatically index and catalogue extracted content for browsing and retrieval.The book analyzes the designs of two novel, working systems for content-based extraction and representation in the support of MPEG-4 and MPEG-7 video standards, respectively. Features of the book include: * Overview of MPEG standards; * A working system for automatic video object segmentation; * A working system for video object query by shape; * Novel technology for a wide range of recognition problems; * Overview of neural network and vision technologies Video Object Extraction and Representation: Theory and Applications will be of interest to research scientists and practitioners working in fields related to the topic. It may also be used as an advanced-level graduate text.

The book deals with the development of a methodology to estimate the motion field between two frames for video coding applications. This book proposes an exhaustive study of the motion estimation process in the framework of a general video coder. The conceptual explanations are discussed in a simple language and with the use of suitable figures. The book will serve as a guide for new researchers working in the field of motion estimation techniques.

Although synthetic environments were traditionally used in military settings for mission rehearsal and simulations, their use is rapidly spreading to a variety of applications in the commercial, research and industrial sectors, such as flight training for commercial aircraft, city planning, car safety research in real-time traffic simulations, and video games. 3D Synthetic Environment Reconstruction contains seven invited chapters from leading experts in the field, bringing together a coherent body of recent knowledge relating 3D geospatial data collection, design issues, and techniques used in synthetic environments design, implementation and interoperability. In particular, this book describes new techniques for the generation of Synthetic Environments with increased resolution and rich attribution, both essential for accurate modeling and simulation. This book also deals with interoperability of models and simulations, which is necessary for facilitating the reuse of modeling and simulation components. 3D Synthetic Environment Reconstruction is an excellent reference for researchers and practitioners in the field.

Matrix transforms are ubiquitous within the world of computer graphics, where they have become an invaluable tool in a programmer's toolkit for solving everything from 2D image scaling to 3D rotation about an arbitrary axis. Virtually every software system and hardware graphics processor uses matrices to undertake operations such as scaling, translation, reflection and rotation. Nevertheless, for some newcomers to the world of computer games and animation, matrix notation can appear obscure and challenging.

Matrices and determinants were originally used to solve groups of simultaneous linear equations, and were subsequently embraced by the computer graphics community to describe the geometric operations for manipulating two- and three-dimensional structures. Consequently, to place matrix notation within an historical context, the author provides readers with some useful background to their development, alongside determinants.

Although it is assumed that the reader is familiar with everyday algebra and the solution of simultaneous linear equations, "Matrix Transforms for Computer Games and Animation" does not expect any prior knowledge of matrix notation. It includes chapters on matrix notation, determinants, matrices, 2D transforms, 3D transforms and quaternions, and includes many worked examples to illustrate their practical use.

Super-Resolution Imaging serves as an essential reference for both academicians and practicing engineers. It can be used both as a text for advanced courses in imaging and as a desk reference for those working in multimedia, electrical engineering, computer science, and mathematics. The first book to cover the new research area of super-resolution imaging, this text includes work on the following groundbreaking topics: * Image zooming based on wavelets and generalized interpolation; * Super-resolution from sub-pixel shifts; * Use of blur as a cue; * Use of warping in super-resolution; * Resolution enhancement using multiple apertures; * Super-resolution from motion data; * Super-resolution from compressed video; * Limits in super-resolution imaging. Written by the leading experts in the field, Super-Resolution Imaging presents a comprehensive analysis of current technology, along with new research findings and directions for future work.

This book constitutes the proceedings of the 4th International Workshop on Motion in Games, held in Edinburgh, UK, in November 2011. The 30 revised full papers presented together with 8 revised poster papers in this volume were carefully reviewed and selected from numerous submissions. The papers are organized in topical sections on character animation, motion synthesis, physically-based character motion, behavior animation, animation systems, crowd simulation, as well as path planning and navigation.

The following chapters of this book presents key issues concerning the neurophysiological aspects of executing cognitive thought processes and the basics of cognitive informatics and new proposals of UBIAS systems dedicated to the meaning-based analysis of selected types of medical images. In particular, to structure the considerations of pattern classification methods, Chapter 2 discusses traditional image recognition techniques and algorithms from the simplest methods based on metric spaces up to methods that use the paradigms of computer image understanding. Chapter 3 deals with the cognitive aspects of brain function. Information from this chapter allows the authors, in a latter part of this book, to show functional analogies between the operation of biological systems and computer implementations. Chapter 4 provides a short compendium of knowledge about the new branch of informatics which formally describes thought processes, namely cognitive informatics. The introduction to subjects of cognitive processes analysed by cognitive informatics will then allow us to introduce new classes of computer systems executing cognitive resonance processes. The following Chapter 5 defines a new class of information systems using cognitive resonance processes. This chapter reviews several proposals of various classes of cognitive categorisation systems put forward by the authors. Chapter 6 contains a broader discussion of the UBIAS system class which the authors proposed for the meaning-based analysis of medical images. Then, Chapter 7 discusses in detail two examples of UBIAS systems built for the semantic classification of foot bone X-rays and images of long bone injuries in extremities. Chapter 8, the last, compiles and summarises information on creating cognitive vision systems designed for the semantic classification of patterns.

The authors present this book to Readers in the hope that it will stir their fascination with the scientific aspects of creating new generation computer systems which imitate thought processes and can determine the meaning of complex image patterns.

A guide on the use of SVMs in pattern classification, including a rigorous performance comparison of classifiers and regressors. The book presents architectures for multiclass classification and function approximation problems, as well as evaluation criteria for classifiers and regressors. Features: Clarifies the characteristics of two-class SVMs; Discusses kernel methods for improving the generalization ability of neural networks and fuzzy systems; Contains ample illustrations and examples; Includes performance evaluation using publicly available data sets; Examines Mahalanobis kernels, empirical feature space, and the effect of model selection by cross-validation; Covers sparse SVMs, learning using privileged information, semi-supervised learning, multiple classifier systems, and multiple kernel learning; Explores incremental training based batch training and active-set training methods, and decomposition techniques for linear programming SVMs; Discusses variable selection for support vector regressors.