Thebookpresentsa cross-sectionofstate-of-the-artresearchonmultimodalc- pora, a highly interdisciplinary area that is a prerequisite for various specialized disciplines. A number of the papers included are revised and expanded versions ofpapersacceptedtotheInternationalWorkshoponMultimodal Corpora: From Models of Natural Interaction to Systems and Applications, held in conjunction th with the 6 International Conference for Language Resources and Evaluation (LREC) on May 27, 2008, in Marrakech, Morocco. This international workshop series started in 2000 and has since then grown into a regular satellite event of the bi-annual LREC conference, attracting researchers from ?elds as diverse as psychology, arti?cial intelligence, robotics, signal processing, computational linguisticsandhuman-computerinteraction. Tocomplement theselected papers from the 2008 workshop, we invited well-known researchers from corpus coll- tioninitiativestocontributetothisvolume. Wewereabletoobtainseveninvited research articles, including contributions from major international multimodal corpus projects like AMI and SmartWeb, which complement the six selected workshop contributions. All papers underwent a special review process for this volume, resulting in signi?cant revisions and extensions based on the experts' advice. While we were pleased that the 2006 edition of the workshop resulted in a special issue of the Journal of Language Resources and Evaluation, published in 2007, we felt that this was the time for another major publication, given not onlytherapidprogressandincreasedinterestin this researchareabut especially in order to acknowledge the di?culty of disseminating results across discipline borders. The Springer LNAI series is the perfect platform for doing so. We also created the website www. multimodal-corpora.

This book constitutes the refereed proceedings of the 15th IAPR International Conference on Discrete Geometry for Computer Imagery, DGCI 2009, held in Montreal, Canada, in September/October 2009.

The 42 revised full papers were carefully reviewed and selected from numerous submissions. The papers are organized in topical sections on discrete shape, representation, recognition and analysis; discrete and combinatorial tools for image segmentation and analysis; discrete and combinatorial Topology; models for discrete geometry; geometric transforms; and discrete tomography.

This book constitutes the research papers presented at the Joint 2101 & 2102 International Conference on Biometric ID Management and Multimodal Communication.

BioID_MultiComm'09 is a joint International Conference organized cooperatively by COST Actions 2101 and 2102. COST 2101 Action is focused on "Biometrics for Identity Documents and Smart Cards (BIDS)," while COST 2102 Action is entitled "Cross-Modal Analysis of Verbal and Non-verbal Communication."

The aim of COST 2101 is to investigate novel technologies for unsupervised multimodal biometric authentication systems using a new generation of biometrics-enabled identity documents and smart cards.

COST 2102 is devoted to develop an advanced acoustical, perceptual and psychological analysis of verbal and non-verbal communication signals originating in spontaneous face-to-face interaction, in order to identify algorithms and automatic procedures capable of recognizing human emotional states.

Biometrics is a rapidly evolving field with applications ranging from accessing one 's computer to gaining entry into a country. The deployment of large-scale biometric systems in both commercial and government applications has increased public awareness of this technology. Recent years have seen significant growth in biometric research resulting in the development of innovative sensors, new algorithms, enhanced test methodologies and novel applications. This book addresses this void by inviting some of the prominent researchers in Biometrics to contribute chapters describing the fundamentals as well as the latest innovations in their respective areas of expertise.

This book constitutes the refereed proceedings of the 7th International Conference on Computer Vision Systems, ICVS 2009, held in Liege, Belgium, October 13-15, 2009.

The 21 papers for oral presentation presented together with 24 poster presentations and 2 invited papers were carefully reviewed and selected from 96 submissions. The papers are organized in topical sections on human-machine-interaction, sensors, features and representations, stereo, 3D and optical flow, calibration and registration, mobile and autonomous systems, evaluation, studies and applications, learning, recognition and adaption.

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.

Everything you ever wanted to know about multimedia retrieval and management. This comprehensive book offers a full picture of the cutting-edge technologies necessary for a profound introduction to the field. Leading experts also cover a broad range of practical applications.

Appendix 164 3. A 3. A. 1 Approximate Estimation of Fundamental Matrix from General Matrix 164 3. A. 2 Estimation of Affine Transformation 165 4 RECOVERY OF EPIPOLAR GEOMETRY FROM LINE SEGMENTS OR LINES 167 Line Segments or Straight Lines 168 4. 1 4. 2 Solving Motion Using Line Segments Between Two Views 173 4. 2. 1 Overlap of Two Corresponding Line Segments 173 Estimating Motion by Maximizing Overlap 175 4. 2. 2 Implementation Details 4. 2. 3 176 Reconstructing 3D Line Segments 4. 2. 4 179 4. 2. 5 Experimental Results 180 4. 2. 6 Discussions 192 4. 3 Determining Epipolar Geometry of Three Views 194 4. 3. 1 Trifocal Constraints for Point Matches 194 4. 3. 2 Trifocal Constraints for Line Correspondences 199 4. 3. 3 Linear Estimation of K, L, and M Using Points and Lines 200 4. 3. 4 Determining Camera Projection Matrices 201 4. 3. 5 Image Transfer 203 4. 4 Summary 204 5 REDEFINING STEREO, MOTION AND OBJECT RECOGNITION VIA EPIPOLAR GEOMETRY 205 5. 1 Conventional Approaches to Stereo, Motion and Object Recognition 205 5. 1. 1 Stereo 205 5. 1. 2 Motion 206 5. 1. 3 Object Recognition 207 5. 2 Correspondence in Stereo, Motion and Object Recognition as 1D Search 209 5. 2. 1 Stereo Matching 209 xi Contents 5. 2. 2 Motion Correspondence and Segmentation 209 5. 2. 3 3D Object Recognition and Localization 210 Disparity and Spatial Disparity Space 210 5.

Despite the fact that images constitute the main objects in computer vision and image analysis, there is remarkably little concern about their actual definition. In this book a complete account of image structure is proposed in terms of rigorously defined machine concepts, using basic tools from algebra, analysis, and differential geometry. Machine technicalities such as discretisation and quantisation details are de-emphasised, and robustness with respect to noise is manifest. From the foreword by Jan Koenderink: It is my hope that the book will find a wide audience, including physicists - who still are largely unaware of the general importance and power of scale space theory, mathematicians - who will find in it a principled and formally tight exposition of a topic awaiting further development, and computer scientists - who will find here a unified and conceptually well founded framework for many apparently unrelated and largely historically motivated methods they already know and love. The book is suited for self-study and graduate courses, the carefully formulated exercises are designed to get to grips with the subject matter and prepare the reader for original research.'

Images and video play a crucial role in visual information systems and multimedia. There is an extraordinary number of applications of such systems in entertainment, business, art, engineering, and science. Such applications often involved large image and video collections, and therefore, searching for images and video in large collections is becoming an important operation. Because of the size of such databases, efficiency is crucial. We strongly believe that image and video retrieval need an integrated approach from fields such as image processing, shape processing, perception, database indexing, visualization, and querying, etc. This book contains a selection of results that was presented at the Dagstuhl Seminar on Content-Based Image and Video Retrieval, in December 1999. The purpose of this seminar was to bring together people from the various fields, in order to promote information exchange and interaction among researchers who are interested in various aspects of accessing the content of image and video data. The book provides an overview of the state of the art in content-based image and video retrieval. The topics covered by the chapters are integrated system aspects, as well as techniques from image processing, computer vision, multimedia, databases, graphics, signal processing, and information theory. The book will be of interest to researchers and professionals in the fields of multimedia, visual information (database) systems, computer vision, and information retrieval.

From the foreword by Thomas Huang:
"During the past decade, researchers in computer vision have found that probabilistic machine learning methods are extremely powerful. This book describes some of these methods. In addition to the Maximum Likelihood framework, Bayesian Networks, and Hidden Markov models are also used. Three aspects are stressed: features, similarity metric, and models. Many interesting and important new results, based on research by the authors and their collaborators, are presented.

Although this book contains many new results, it is written in a style that suits both experts and novices in computer vision."

Conceptually, a database consists of objects and relationships. Object Relationship Notation (ORN) is a simple notation that more precisely defines relationships by combining UML multiplicities with uniquely defined referential actions.

This book shows how ORN can be used in UML class diagrams and database definition languages (DDLs) to better model and implement relationships and thus more productively develop database applications. For the database developer, it presents many examples of relationships modeled using ORN-extended class diagrams and shows how these relationships are easily mapped to an ORN-extended SQL or Object DDL. For the DBMS developer, it presents the specifications and algorithms needed to implement ORN in a relational and object DBMS.

This book also describes tools that can be downloaded or accessed via the Web. These tools allow databases to be modeled using ORN and implemented using automatic code generation that adds ORN support to Microsoft SQL Server and Progress Object Store.

Object Relationship Notation (ORN) for Database Applications: Enhancing the Modeling and Implementation of Associations is written for research scientists, research libraries, professionals, and 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.

Computer security - the protection of data and computer systems from intentional, malicious intervention - is attracting increasing attention. Much work has gone into development of tools to detect ongoing or already perpetrated attacks, but a key shortfall in current intrusion detection systems is the high number of false alarms they produce. This book analyzes the false alarm problem, then applies results from the field of information visualization to the problem of intrusion detection. Four different visualization approaches are presented, mainly applied to data from web server access logs.

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.

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.

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.

This is the first book which informs about recent progress in biomechanics, computer vision and computer graphics - all in one volume. Researchers from these areas have contributed to this book to promote the establishment of human motion research as a multi-facetted discipline and to improve the exchange of ideas and concepts between these three areas. The book combines carefully written reviews with detailed reports on recent progress in research.

The authors here provide a detailed treatment of the design of robust adaptive controllers for nonlinear systems with uncertainties. They employ a new tool based on the ideas of system immersion and manifold invariance. New algorithms are delivered for the construction of robust asymptotically-stabilizing and adaptive control laws for nonlinear systems. The methods proposed lead to modular schemes that are easier to tune than their counterparts obtained from Lyapunov redesign.

The application of Computational Intelligence in emerging research areas such as Granular Computing, Mechatronics, and Bioinformatics shows its usefulness often emphasized by Prof Lotfi Zadeh, the inventor of fuzzy logic and many others. This book contains recent advances in Computational Intelligence methods for modeling, optimization and prediction and covers a large number of applications. The book presents new Computational Intelligence theory and methods for modeling and prediction. The range of the various applications is captured with 5 chapters in image processing, 2 chapters in audio processing, 3 chapters in commerce and finance, 2 chapters in communication networks and 6 chapters containing other applications.

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.

Motion-Free Super-Resolution is a compilation of very recent work on various methods of generating super-resolution (SR) images from a set of low-resolution images. The current literature on this topic deals primarily with the use of motion cues for the purpose of generating SR images. These cues have, it is shown, their advantages and disadvantages. In contrast, this book shows that cues other than motion can also be used for the same purpose, and addresses both the merits and demerits of these new techniques.

Motion-Free Super-Resolution supersedes much of the lead author 's previous edited volume, "Super-Resolution Imaging," and includes an up-to-date account of the latest research efforts in this fast-moving field. This sequel also features a style of presentation closer to that of a textbook, with an emphasis on teaching and explanation rather than scholarly presentation.

Since the dawn of the new millennium, robotics has undergone a major transf- mation in scope and dimensions. This expansion has been brought about by the maturityofthe?eldandtheadvancesinitsrelatedtechnologies.Fromapred- inantly industrial focus, robotics has been rapidly expanding into the challenges of the human world. The new generation of robots is expected to safely and dependably cohabit with humans in homes, workplaces, and communities, p- viding support in services, entertainment, education, healthcare, manufacturing, and assistance. Beyond its impact on physical robots, the body of knowledge robotics has produced is revealing a much wider rangeof applications reaching across diverse research areas and scienti?c disciplines, such as: biomechanics, haptics, neu- sciences, virtual prototyping, animation, surgery, and sensor networks among others. In return, the challenges of the new emerging areas are proving an ab- dant source of stimulation and insights for the ?eld of robotics. It is indeed at the intersection of disciplines that the most striking advances happen. The goal of the series of Springer Tracts in Advanced Robotics (STAR)isto bring, in a timely fashion, the latest advances and developments in robotics on thebasisoftheirsigni?canceandquality.Itisourhopethatthewiderdissemi- tion of research developments will stimulate more exchanges and collaborations among the research community and contribute to further advancement of this rapidly growing ?e

Networked computers are ubiquitous, and are subject to attack, misuse, and abuse. One method to counteracting this cyber threat is to provide security analysts with better tools to discover patterns, detect anomalies, identify correlations, and communicate their findings. Visualization for computer security (VizSec) researchers and developers are doing just that. VizSec is about putting robust information visualization tools into the hands of human analysts to take advantage of the power of the human perceptual and cognitive processes in solving computer security problems. This volume collects the papers presented at the 4th International Workshop on Computer Security - VizSec 2007.

One of the grand challenges for computational intelligence and biometrics is to understand how people process and recognize faces and to develop automated and reliable face recognition systems. Biometrics has become the major component in the complex decision making process associated with security applications. The many challenges addressed for face detection and authentication include cluttered environments, occlusion and disguise, temporal changes, and last but not least, robust training and open set testing.

Reliable Face Recognition Methods seeks to comprehensively address the face recognition problem while drawing inspiration and gaining new insights from complementary fields of endeavor such as neurosciences, statistics, signal and image processing, computer vision, and machine learning and data mining. The book examines the evolution of research surrounding the field to date, explores new directions, and offers specific guidance on the most promising venues for future R&D.

With its well-focused approach and clarity of presentation, this new text/reference is an excellent resource for computer scientists and engineers, researchers, and professionals who need to learn about face recognition. In addition, the book is ideally suited to students studying biometrics, pattern recognition, and human-computer interaction.