Traditionally, scientific fields have defined boundaries, and scientists work on research problems within those boundaries. However, from time to time those boundaries get shifted or blurred to evolve new fields. For instance, the original goal of computer vision was to understand a single image of a scene, by identifying objects, their structure, and spatial arrangements. This has been referred to as image understanding. Recently, computer vision has gradually been making the transition away from understanding single images to analyzing image sequences, or video understanding. Video understanding deals with understanding of video sequences, e. g., recognition of gestures, activities, facial expressions, etc. The main shift in the classic paradigm has been from the recognition of static objects in the scene to motion-based recognition of actions and events. Video understanding has overlapping research problems with other fields, therefore blurring the fixed boundaries. Computer graphics, image processing, and video databases have obvious overlap with computer vision. The main goal of computer graphics is to gener ate and animate realistic looking images, and videos. Researchers in computer graphics are increasingly employing techniques from computer vision to gen erate the synthetic imagery. A good example of this is image-based rendering and modeling techniques, in which geometry, appearance, and lighting is de rived from real images using computer vision techniques. Here the shift is from synthesis to analysis followed by synthesis."

MPEG-4 is the multimedia standard for combining interactivity, natural and synthetic digital video, audio and computer-graphics. Typical applications are: internet, video conferencing, mobile videophones, multimedia cooperative work, teleteaching and games. With MPEG-4 the next step from block-based video (ISO/IEC MPEG-1, MPEG-2, CCITT H.261, ITU-T H.263) to arbitrarily-shaped visual objects is taken. This significant step demands a new methodology for system analysis and design to meet the considerably higher flexibility of MPEG-4. Motion estimation is a central part of MPEG-1/2/4 and H.261/H.263 video compression standards and has attracted much attention in research and industry, for the following reasons: it is computationally the most demanding algorithm of a video encoder (about 60-80% of the total computation time), it has a high impact on the visual quality of a video encoder, and it is not standardized, thus being open to competition. Algorithms, Complexity Analysis, and VLSI Architectures for MPEG-4 Motion Estimation covers in detail every single step in the design of a MPEG-1/2/4 or H.261/H.263 compliant video encoder: Fast motion estimation algorithms Complexity analysis tools Detailed complexity analysis of a software implementation of MPEG-4 video Complexity and visual quality analysis of fast motion estimation algorithms within MPEG-4 Design space on motion estimation VLSI architectures Detailed VLSI design examples of (1) a high throughput and (2) a low-power MPEG-4 motion estimator. Algorithms, Complexity Analysis and VLSI Architectures for MPEG-4 Motion Estimation is an important introduction to numerous algorithmic, architectural and system design aspects of the multimedia standard MPEG-4. As such, all researchers, students and practitioners working in image processing, video coding or system and VLSI design will find this book of interest.

This volume presents high quality, state-of-the-art research ideas and results from theoretic, algorithmic and application viewpoints. It contains contributions by leading experts in the obsequious scientific and technological field of multimedia. The book specifically focuses on interaction with multimedia content with special emphasis on multimodal interfaces for accessing multimedia information. The book is designed for a professional audience composed of practitioners and researchers in industry. It is also suitable for advanced-level students in computer science.

Medical imaging has been transformed over the past 30 years by the advent of computerized tomography (CT), magnetic resonance imaging (MRI), and various advances in x-ray and ultrasonic techniques. An enabling force behind this progress has been the (so far) exponentially increasing power of computers, which has made it practical to explore fundamentally new approaches. In particular, what our group terms "model-based" modalities-which produce tissue property images from data using nonlinear, iterative numerical modeling techniques-have become increasingly feasible.

Alternative Breast Imaging: Four Model-Based Approaches explores our research on four such modalities, particularly with regard to imaging of the breast: (1) MR elastography (MRE), (2) electrical impedance spectroscopy (EIS), (3) microwave imaging spectroscopy (MIS), and (4) near infrared spectroscopic imaging (NIS). Chapter 1 introduces the present state of breast imaging and discusses how our alternative modalities can contribute to the field. Chapter 2 looks at the computational common ground shared by all four modalities. Chapters 2 through 10 are devoted to the four modalities, with each modality being discussed first in a theory chapter and then in an implementation-and-results chapter. The eleventh and final chapter discusses statistical methods for image analysis in the context of these four alternative imaging modalities.

Imaging for the detection of breast cancer is a particularly interesting and relevant application of the four imaging modalities discussed in this book. Breast cancer is an extremely common health problem for women; the National Cancer Institute estimates that one in eight US women will develop breast cancer at least once in her lifetime. Yet the efficacy of the standard (and notoriously uncomfortable) early-detection test, the x-ray mammogram, has been disputed of late, especially for younger women. Conditions are thus ripe for the development of affordable techniques that replace or complement mammography. The breast is both anatomically accessible and small enough that the computing power required to model it, is affordable.

In The Brain from 25,000 Feet, Mark A. Changizi defends a non-reductionist philosophy and applies it to a variety of problems in the brain sciences. Some of the key questions answered are as follows. Why do we see visual illusions, and why are illusions inevitable for any finite-speed vision machine? Why aren't brains universal learning machines, and what does the riddle of induction and its solution have to do with human learning and innateness? The author tackles such questions as why the brain is folded, and why animals have as many limbs as they do, explaining how these relate to principles of network optimality. He describes how most natural language words are vague and then goes on to explain the connection to the ultimate computational limits on machines. There is also a fascinating discussion of how animals accommodate greater behavioral complexity. This book is a must-read for researchers interested in taking a high-level, non-mechanistic approach to answering age-old fundamental questions in the brain sciences.

Scale is a concept the antiquity of which can hardly be traced. Certainly the familiar phenomena that accompany sc ale changes in optical patterns are mentioned in the earliest written records. The most obvious topological changes such as the creation or annihilation of details have been a topic to philosophers, artists and later scientists. This appears to of fascination be the case for all cultures from which extensive written records exist. For th instance, chinese 17 c artist manuals remark that "distant faces have no eyes" . The merging of details is also obvious to many authors, e. g. , Lucretius mentions the fact that distant islands look like a single one. The one topo logical event that is (to the best of my knowledge) mentioned only late (by th John Ruskin in his "Elements of drawing" of the mid 19 c) is the splitting of a blob on blurring. The change of images on a gradual increase of resolu tion has been a recurring theme in the arts (e. g. , the poetic description of the distant armada in Calderon's The Constant Prince) and this "mystery" (as Ruskin calls it) is constantly exploited by painters.

This book contains the proceedings of the International Symposium on Mathematical Morphology and its Applications to Image and Signal Processing IV, held June 3-5, 1998, in Amsterdam, The Netherlands. The purpose of the work is to provide the image analysis community with a sampling of recent developments in theoretical and practical aspects of mathematical morphology and its applications to image and signal processing. Among the areas covered are: digitization and connectivity, skeletonization, multivariate morphology, morphological segmentation, color image processing, filter design, gray-scale morphology, fuzzy morphology, decomposition of morphological operators, random sets and statistical inference, differential morphology and scale-space, morphological algorithms and applications. Audience: This volume will be of interest to research mathematicians and computer scientists whose work involves mathematical morphology, image and signal processing.

After 20 years of pursuing rough set theory and its applications a look on its present state and further prospects is badly needed. The monograph Rough Set Theory and Granular Computing edited by Masahiro Inuiguchi, Shoji Hirano and Shusaku Tsumoto meets this demand. It presents the newest developments in this area and gives fair picture of the state of the art in this domain. Firstly, in the keynote papers by Zdzislaw Pawlak, Andrzej Skowron and Sankar K. Pal the relationship of rough sets with other important methods of data analysis -Bayes theorem, neuro computing and pattern recognitio- is thoroughly examined. Next, several interesting generalizations of the the ory and new directions of research are presented. Furthermore application of rough sets in data mining, in particular, rule induction methods based on rough set theory is presented and discussed. Further important issue dis cussed in the monograph is rough set based data analysis, including study of decisions making in conflict situations. Last but not least, some recent engi neering applications of rough set theory are given. They include a proposal of rough set processor architecture organization for fast implementation of ba sic rough set operations and discussion of results concerning advanced image processing for unmanned aerial vehicle. Thus the monograph beside presenting wide spectrum of ongoing research in this area also points out new emerging areas of study and applications, which makes it a valuable source of information to all interested in this do main."

Integrating Graphics and Vision for Object Recognition serves as a reference for electrical engineers and computer scientists researching computer vision or computer graphics. Computer graphics and computer vision can be viewed as different sides of the same coin. In graphics, algorithms are given knowledge about the world in the form of models, cameras, lighting, etc., and infer (or render) an image of a scene. In vision, the process is the exact opposite: algorithms are presented with an image, and infer (or interpret) the configuration of the world. This work focuses on using computer graphics to interpret camera images: using iterative rendering to predict what should be visible by the camera and then testing and refining that hypothesis. Features of the book include: Many illustrations to supplement the text; A novel approach to the integration of graphics and vision; Genetic algorithms for vision; Innovations in closed loop object recognition. Integrating Graphics and Vision for Object Recognition 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.

One of the most natural representations for modelling spatial objects in computers is discrete representations in the form of a 2D square raster and a 3D cubic grid, since these are naturally obtained by segmenting sensor images. However, the main difficulty is that discrete representations are only approximations of the original objects, and can only be as accurate as the cell size allows. If digitisation is done by real sensor devices, then there is the additional difficulty of sensor distortion. To overcome this, digital shape features must be used that abstract from the inaccuracies of digital representation. In order to ensure the correspondence of continuous and digital features, it is necessary to relate shape features of the underlying continuous objects and to determine the necessary resolution of the digital representation. This volume gives an overview and a classification of the actual approaches to describe the relation between continuous and discrete shape features that are based on digital geometric concepts of discrete structures. Audience: This book will be of interest to researchers and graduate students whose work involves computer vision, image processing, knowledge representation or representation of spatial objects.

In recent years 3D geo-information has become an important research area due to the increased complexity of tasks in many geo-scientific applications, such as sustainable urban planning and development, civil engineering, risk and disaster management and environmental monitoring. Moreover, a paradigm of cross-application merging and integrating of 3D data is observed. The problems and challenges facing today's 3D software, generally application-oriented, focus almost exclusively on 3D data transportability issues - the ability to use data originally developed in one modelling/visualisation system in other and vice versa. Tools for elaborated 3D analysis, simulation and prediction are either missing or, when available, dedicated to specific tasks. In order to respond to this increased demand, a new type of system has to be developed. A fully developed 3D geo-information system should be able to manage 3D geometry and topology, to integrate 3D geometry and thematic information, to analyze both spatial and topological relationships, and to present the data in a suitable form. In addition to the simple geometry types like point line and polygon, a large variety of parametric representations, freeform curves and surfaces or sweep shapes have to be supported. Approaches for seamless conversion between 3D raster and 3D vector representations should be available, they should allow analysis of a representation most suitable for a specific application.

In this book, research and development trends of physics, engineering, mathematics and computer sciences in biomedical engineering are presented. Contributions from industry, clinics, universities and research labs with foci on medical imaging (CT, MRT, US, PET, SPECT etc.), medical image processing (segmentation, registration, visualization etc.), computer-assisted surgery (medical robotics, navigation), biomechanics (motion analysis, accident research, computer in sports, ergonomics etc.), biomedical optics (OCT, soft-tissue optics, optical monitoring etc.) and laser medicine (tissue ablation, gas analytics, topometry etc.) give insight to recent engineering, clinical and mathematical studies.

By virtue of their special algebraic structures, Pythagorean-hodograph (PH) curves offer unique advantages for computer-aided design and manufacturing, robotics, motion control, path planning, computer graphics, animation, and related fields. This book offers a comprehensive and self-contained treatment of the mathematical theory of PH curves, including algorithms for their construction and examples of their practical applications. It emphasizes the interplay of ideas from algebra and geometry and their historical origins and includes many figures, worked examples, and detailed algorithm descriptions.

Although computer graphics games and animations have been popular for more than a decade, recently personal computers evolved to support real-time, realistic-looking interactive games. OpenGL, a technology standard to develop CG applications, has had incredible momentum in both the professional and consumer markets. Once only the domain of production houses, OpenGL has grown to be the standard for graphics programming on all platforms, personal computers, and workstations. Now more than ever, people are eager to learn about what it takes to make such productions, and how they can be a part of them. Current literature on how to make movies/games focus more on the technology (OpenGL, DirectX, etc) and their APIs rather than on the principles of computer graphics. However, understanding these principles is the key to dealing with any technology API. The aim of "Principles of Computer Graphics and OpenGL" is to teach readers the principles of computer graphics. Hands-on examples developed in OpenGL illustrate the key concepts, and readers develop a professional animation, following traditional processes used in production houses. By the end of the book, readers will be experts in the principles of computer graphics and OpenGL. They will be able to develop their own professional quality games via the same approach used in production houses.

The problem of scale pervades both the natural sciences and the vi sual arts. The earliest scientific discussions concentrate on visual per ception (much like today ) and occur in Euclid's (c. 300 B. C. ) Optics and Lucretius' (c. 100-55 B. C. ) On the Nature of the Universe. A very clear account in the spirit of modern "scale-space theory" is presented by Boscovitz (in 1758), with wide ranging applications to mathemat ics, physics and geography. Early applications occur in the cartographic problem of "generalization," the central idea being that a map in order to be useful has to be a "generalized" (coarse grained) representation of the actual terrain (Miller and Voskuil 1964). Broadening the scope asks for progressive summarizing. Very much the same problem occurs in the (realistic) artistic rendering of scenes. Artistic generalization has been analyzed in surprising detail by John Ruskin (in his Modern Painters), who even describes some of the more intricate generic "scale-space sin gularities" in detail: Where the ancients considered only the merging of blobs under blurring, Ruskin discusses the case where a blob splits off another one when the resolution is decreased, a case that has given rise to confusion even in the modern literature."

This monograph covers theoretical aspects of simultaneous localization and map building for mobile robots. These include estimation stability, nonlinear models for the propagation of uncertainties, temporal landmark compatibility, as well as issues pertaining the coupling of control and SLAM. One of the most relevant topics covered in this monograph is the theoretical formalism of partial observability in SLAM.

This book covers the MPEG H.264 and MS VC-1 video coding standards as well as issues in broadband video delivery over IP networks. This professional reference is designed for industry practitioners, including video engineers, and professionals in consumer electronics, telecommunications and media compression industries. The book is also suitable as a secondary text for advanced-level students in computer science and electrical engineering.

3D Face Processing: Modeling, Analysis and Synthesis introduces the frontiers of 3D face processing techniques. It reviews existing 3D face processing techniques, including techniques for 3D face geometry modeling; 3D face motion modeling; and 3D face motion tracking and animation. Then it discusses a unified framework for face modeling, analysis and synthesis. In this framework, the authors present new methods for modeling complex natural facial motion, as well as face appearance variations due to illumination and subtle motion. Then the authors apply the framework to face tracking, expression recognition and face avatar for HCI interface. They conclude this book with comments on future work in the 3D face processing framework.
3D Face Processing: Modeling, Analysis and Synthesis will interest those working in face processing for intelligent human computer interaction and video surveillance. It contains a comprehensive survey on existing face processing techniques, which can serve as a reference for students and researchers. It also covers in-depth discussion on face motion analysis and synthesis algorithms, which will benefit more advanced graduate students and researchers.

Assembled in this volume is a collection of some of the state-of-the-art methods that are using computer vision and machine learning techniques as applied in robotic applications. Currently there is a gap between research conducted in the computer vision and robotics communities. This volume discusses contrasting viewpoints of computer vision vs. robotics, and provides current and future challenges discussed from a research perspective.

This book traces progress in photography since the first pinhole, or camera obscura, architecture. The authors describe innovations such as photogrammetry, and omnidirectional vision for robotic navigation. The text shows how new camera architectures create a need to master related projective geometries for calibration, binocular stereo, static or dynamic scene understanding. Written by leading researchers in the field, this book also explores applications of alternative camera architectures.

A sharp increase in the computing power of modern computers has triggered the development of powerful algorithms that can analyze complex patterns in large amounts of data within a short time period. Consequently, it has become possible to apply pattern recognition techniques to new tasks. The main goal of this book is to cover some of the latest application domains of pattern recognition while presenting novel techniques that have been developed or customized in those domains.

The application of geometric algebra to the engineering sciences is a young, active subject of research. The promise of this field is that the mathematical structure of geometric algebra together with its descriptive power will result in intuitive and more robust algorithms.

This book examines all aspects essential for a successful application of geometric algebra: the theoretical foundations, the representation of geometric constraints, and the numerical estimation from uncertain data. Formally, the book consists of two parts: theoretical foundations and applications. The first part includes chapters on random variables in geometric algebra, linear estimation methods that incorporate the uncertainty of algebraic elements, and the representation of geometry in Euclidean, projective, conformal and conic space. The second part is dedicated to applications of geometric algebra, which include uncertain geometry and transformations, a generalized camera model, and pose estimation.

Graduate students, scientists, researchers and practitioners will benefit from this book. The examples given in the text are mostly recent research results, so practitioners can see how to apply geometric algebra to real tasks, while researchers note starting points for future investigations. Students will profit from the detailed introduction to geometric algebra, while the text is supported by the author's visualization software, CLUCalc, freely available online, and a website that includes downloadable exercises, slides and tutorials.

Multimodal Video Characterization and Summarization is a valuable research tool for both professionals and academicians working in the video field.

This book describes the methodology for using multimodal audio, image, and text technology to characterize video content. This new and groundbreaking science has led to many advances in video understanding, such as the development of a video summary. Applications and methodology for creating video summaries are described, as well as user-studies for evaluation and testing.

A representation of objects by their parts is the dominant strategy for representing complex 3D objects in many disciplines. In computer vision and robotics, superquadrics are among the most widespread part models. Superquadrics are a family of parametric models that cover a wide variety of smoothly changing 3D symmetric shapes, which are controlled with a small number of parameters and which can be augmented with the addition of global and local deformations. The book covers, in depth, the geometric properties of superquadrics. The main contribution of the book is an original approach to the recovery and segmentation of superquadrics from range images. Several applications of superquadrics in computer vision and robotics are thoroughly discussed and, in particular, the use of superquadrics for range image registration is demonstrated. Audience: The book is intended for readers of all levels who are familiar with and interested in computer vision issues.

This book brings together aspects of statistics and machine learning to provide a comprehensive guide to evaluating, interpreting and understanding biometric data. It naturally leads to topics including data mining and prediction to be examined in detail. The book places an emphasis on the various performance measures available for biometric systems, what they mean, and when they should and should not be applied. The evaluation techniques are presented rigorously, however they are always accompanied by intuitive explanations. This is important for the increased acceptance of biometrics among non-technical decision makers, and ultimately the general public.