This volume brings together the peer-reviewed contributions of the participants at the COST 2102 International Conference on "Cross-Modal Analysis of Speech, Gestures, Gaze and Facial Expressions" held in Prague, Czech Republic, October 15-18, 2008. The conference was sponsored by COST (European Cooperation in the Field of Scientific and Technical Research, www. cost. esf. org/domains_actions/ict) in the - main of Information and Communication Technologies (ICT) for disseminating the research advances developed within COST Action 2102: "Cross-Modal Analysis of Verbal and Nonverbal Communication" http://cost2102. cs. stir. ac. uk. COST 2102 research networking has contributed to modifying the conventional theoretical approach to the cross-modal analysis of verbal and nonverbal communi- tion changing the concept of face to face communication with that of body to body communication as well as developing the idea of embodied information. Information is no longer the result of a difference in perception and is no longer measured in terms of quantity of stimuli, since the research developed in COST 2102 has proved that human information processing is a nonlinear process that cannot be seen as the sum of the numerous pieces of information available. Considering simply the pieces of inf- mation available, results in a model of the receiver as a mere decoder, and produces a huge simplification of the communication process.

INSTICC organized the third edition of VISIGRAPP that took place in Funchal- Madeira, Portugal in January 2008 after successful previous editions. This book - cludes selected papers from VISIGRAPP 2008, the Joint Conference on Computer Vision Theory and Applications (VISAPP) and Computer Graphics Theory and - plications (GRAPP). The conference was intended to stimulate the exchange of ideas on the topics of c- puter vision and computer graphics. We received a high number of paper submissions: 374 in total for both conferences. We had contributions from more than 50 countries in all continents. This confirms the success and global dimension of these jointly organized conferences. After a rigorous double-blind evaluation method, 78 submissions were accepted as full papers. From those, 20 were selected for this book. To ensure the sci- tific quality of the contributions, these were selected from the ones that were evaluated with the highest scores by the VISIGRAPP Program Committee Members and then they were extended and revised by the authors. Special thanks go to all contributors and re- rees, without whom this book would not have been possible. VISIGRAPP 2008 also featured the comments of keynote speakers, in alphabetical order, Adrian Hilton (University of Surrey, UK), Genevieve Lucet (Computer S- vices for Research at the UNAM, Mexico), Peter Sturm (INRIA Rhone-Alpes, France) and Sharathchandra Pankanti (IBM - Exploratory Computer Vision Group, USA), who are internationally recognized researchers. The presentations represented an - portant contribution to the overall quality of the conference.

Welcome to the 2008EuropeanConference onComputer Vision. These proce- ings are the result of a great deal of hard work by many people. To produce them, a total of 871 papers were reviewed. Forty were selected for oral pres- tation and 203 were selected for poster presentation, yielding acceptance rates of 4.6% for oral, 23.3% for poster, and 27.9% in total. Weappliedthreeprinciples.First, sincewehadastronggroupofAreaChairs, the ?nal decisions to accept or reject a paper rested with the Area Chair, who wouldbeinformedbyreviewsandcouldactonlyinconsensuswithanotherArea Chair. Second, we felt that authors were entitled to a summary that explained how the Area Chair reached a decision for a paper. Third, we were very careful to avoid con?icts of interest. Each paper was assigned to an Area Chair by the Program Chairs, and each Area Chair received a pool of about 25 papers. The Area Chairs then identi?ed and rankedappropriatereviewersfor eachpaper in their pool, and a constrained optimization allocated three reviewers to each paper. We are very proud that every paper received at least three reviews. At this point, authors wereable to respond to reviews. The Area Chairs then needed to reach a decision. We used a series of procedures to ensure careful review and to avoid con?icts of interest. ProgramChairs did not submit papers. The Area Chairs were divided into three groups so that no Area Chair in the group was in con?ict with any paper assigned to any Area Chair in the group

This book constitutes the refereed proceedings of the 13th Iberoamerican Congress on Pattern Recognition, CIARP 2008, held in Havana, Cuba, in September 2008.

The 93 revised full papers presented together with 3 keynote articles were carefully reviewed and selected from 182 submissions. The papers are organized in topical sections on signal analysis for characterization and filtering, analysis of shape and texture, analysis of speech and language, data mining, clustering of images and documents, statistical pattern recognition, classification and description of objects, classification and edition, geometric image analysis, neural networks, computer vision, image coding, associative memories and neural networks, interpolation and video tracking, images analysis, music and speech analysis, as well as classifier combination and document filtering.

Following the very successful Motion in Games event in June 2008, we or- nized the Second International Workshop on Motion in Games (MIG) during November 21-24, 2009 in Zeist, The Netherlands. Games have become a very important medium for both education and - tertainment. Motion plays a crucial role in computer games. Characters move around, objects are manipulated or move due to physical constraints, entities are animated, and the camera moves through the scene. Even the motion of the player nowadays is used as input to games. Motion is currently studied in many di?erent areas of research, including graphics and animation, game technology, robotics, simulation, computer vision, and also physics, psychology, and urban studies. Cross-fertilizationbetween these communities can considerably advance the state of the art in this area. The goal of the workshop Motion in Games is to bring together researchers from this variety of ?elds to present the most recent results and to initiate collaboration. The workshop is organized by the Dutch research project GATE. In total, the workshop this year consisted of 27 high-quality presentations by a selection of internationally renownedspeakers in the ?eld of games and simulations. We were extremely pleased with the quality of the contributions to the MIG workshop and we look forward to organizing a follow-up MIG event.

Cognitive computing simulates human thought processes with self-learning algorithms that utilize data mining, pattern recognition, and natural language processing. The integration of deep learning improves the performance of Cognitive computing systems in many applications, helping in utilizing heterogeneous data sets and generating meaningful insights.

This Lecture Notes in Computer Science (LNCS) volume contains the papers presented at the Second International Workshop on Computational Forensics (IWCF 2008), held August 7-8, 2008. It was a great honor for the organizers to host this scienti?c event at the renowned National Academy of Sciences: Keck Center in Washington, DC, USA. Computational Forensics is an emerging research domain focusing on the investigation of forensic problems using computational methods. Its primary goalis the discoveryand advancement of forensicknowledgeinvolving modeling, computer simulation, and computer-based analysis and recognition in studying and solving forensic problems. The Computational Forensics workshop series is intended as a forum for researchers and practitioners in all areas of computational and forensic sciences. This forum discusses current challenges in computer-assisted forensic investi- tions and presents recent progress and advances. IWCF addresses a broad spectrum of forensic disciplines that use computer tools for criminal investigation. This year's edition covers presentations on c- putational methods for individuality studies, computer-based3D processing and analysis of skulls and human bodies, shoe print preprocessing and analysis, n- ural language analysis and information retrieval to support law enforcement, analysis and group visualization of speech recordings, scanner and print device forensics, and computer-based questioned document and signature analysis.

This book contains a selection of higher quality and reviewed papers of the 14th Portuguese Conference on Artificial Intelligence, EPIA 2009, held in Aveiro, Portugal, in October 2009.

The 55 revised full papers presented were carefully reviewed and selected from a total of 163 submissions.

The papers are organized in topical sections on artificial intelligence in transportation and urban mobility (AITUM), artificial life and evolutionary algorithms (ALEA), computational methods in bioinformatics and systems biology (CMBSB), computational logic with applications (COLA), emotional and affective computing (EAC), general artificial intelligence (GAI), intelligent robotics (IROBOT), knowledge discovery and business intelligence (KDBI), muli-agent systems (MASTA) social simulation and modelling (SSM), text mining and application (TEMA) as well as web and network intelligence (WNI).

This book constitutes the refereed proceedings of the 11th International Conference on Advanced Concepts for Intelligent Vision Systems, ACIVS 2009, held in Bordeaux, France in September/October 2009.

The 43 revised full papers and 25 posters presented were carefully reviewed and selected from 115 submissions. The papers are organized in topical sections on technovision, fundamental mathematical techniques, image processing, coding and filtering, image and video analysis, computer vision, tracking, color, multispectral and special-purpose imaging, medical imaging, and biometrics.

This book constitutes the refereed proceedings of HCI and Usability for e-Inclusion, held as the 5th Symposium of the Workgroup Human-Computer Interaction and Usability Engineering of the Austrian Computer Society, USAB 2009, in Linz, Austria, in November 2009.

The 12 revised full papers and 26 revised short papers presented were carefully reviewed and selected from 60 submissions. The papers are organized in topical sections on gender and cognitive performance, usefulness, usability, accessibility, emotion, confidence and elderly, usability testing, evaluation, measurement, education, learning and e-inclusion, design for adaptive content processing, grounded theory, activity theory and situated action, smart home, health and ambient assistent living, user centred design and usability practice, interaction, assistive technologies and virtual environments, communication, interfaces and haptic technology as well as new technologies and challenges for people with disabilities.

Overthelastdecades, energyminimizationmethods havebecomeanestablished paradigm to resolve a variety of challenges in the ?elds of computer vision and pattern recognition. While traditional approaches to computer vision were often based on a heuristic sequence of processing steps and merely allowed very l- ited theoretical understanding of the respective methods, most state-of-the-art methods are nowadays based on the concept of computing solutions to a given problem by minimizing respective energies. This volume contains the papers presented at the 7th International Conf- ence on Energy Minimization Methods in Computer Vision and Pattern Rec- nition (EMMCVPR 2009), held at the University of Bonn, Germany, August 24-28, 2009. These papers demonstrate that energy minimization methods have become a mature ?eld of research spanning a broad range of areas from discrete graph theoretic approaches and Markov random ?elds to variational methods and partial di?erential equations. Application areas include image segmentation and tracking, shape optimization and registration, inpainting and image deno- ing, color and texture modeling, statistics and learning. Overall, we received 75 high-quality double-blind submissions. Based on the reviewer recommendations, 36paperswereselectedforpublication,18asoraland18asposterpresentations. Both oral and poster papers were attributed the same number of pages in the conference proceedings. Furthermore, we were delighted that three leading experts from the ?elds of computer vision and energy minimization, namely, Richard Hartley (C- berra, Australia), Joachim Weickert (Saarbruc ] ken, Germany) and Guillermo Sapiro(Minneapolis, USA)agreedtofurtherenrichtheconferencewithinspiring keynote lectures.

The First Asian Conference on Machine Learning (ACML 2009) was held at Nanjing, China during November 2-4, 2009.This was the ?rst edition of a series of annual conferences which aim to provide a leading international forum for researchers in machine learning and related ?elds to share their new ideas and research ?ndings. This year we received 113 submissions from 18 countries and regions in Asia, Australasia, Europe and North America. The submissions went through a r- orous double-blind reviewing process. Most submissions received four reviews, a few submissions received ?ve reviews, while only several submissions received three reviews. Each submission was handled by an Area Chair who coordinated discussions among reviewers and made recommendation on the submission. The Program Committee Chairs examined the reviews and meta-reviews to further guarantee the reliability and integrity of the reviewing process. Twenty-nine - pers were selected after this process. To ensure that important revisions required by reviewers were incorporated into the ?nal accepted papers, and to allow submissions which would have - tential after a careful revision, this year we launched a "revision double-check" process. In short, the above-mentioned 29 papers were conditionally accepted, and the authors were requested to incorporate the "important-and-must"re- sionssummarizedbyareachairsbasedonreviewers'comments.Therevised?nal version and the revision list of each conditionally accepted paper was examined by the Area Chair and Program Committee Chairs. Papers that failed to pass the examination were ?nally rejected.

The 13th International Conference on Human-Computer Interaction, HCI Inter- tional 2009, was held in San Diego, California, USA, July 19-24, 2009, jointly with the Symposium on Human Interface (Japan) 2009, the 8th International Conference on Engineering Psychology and Cognitive Ergonomics, the 5th International Conference on Universal Access in Human-Computer Interaction, the Third International Conf- ence on Virtual and Mixed Reality, the Third International Conference on Internati- alization, Design and Global Development, the Third International Conference on Online Communities and Social Computing, the 5th International Conference on Augmented Cognition, the Second International Conference on Digital Human Mod- ing, and the First International Conference on Human Centered Design. A total of 4,348 individuals from academia, research institutes, industry and gove- mental agencies from 73 countries submitted contributions, and 1,397 papers that were judged to be of high scientific quality were included in the program. These papers - dress the latest research and development efforts and highlight the human aspects of the design and use of computing systems. The papers accepted for presentation thoroughly cover the entire field of human-computer interaction, addressing major advances in knowledge and effective use of computers in a variety of application areas.

Similarity-based learning methods have a great potential as an intuitive and ?exible toolbox for mining, visualization,and inspection of largedata sets. They combine simple and human-understandable principles, such as distance-based classi?cation, prototypes, or Hebbian learning, with a large variety of di?erent, problem-adapted design choices, such as a data-optimum topology, similarity measure, or learning mode. In medicine, biology, and medical bioinformatics, more and more data arise from clinical measurements such as EEG or fMRI studies for monitoring brain activity, mass spectrometry data for the detection of proteins, peptides and composites, or microarray pro?les for the analysis of gene expressions. Typically, data are high-dimensional, noisy, and very hard to inspect using classic (e. g. , symbolic or linear) methods. At the same time, new technologies ranging from the possibility of a very high resolution of spectra to high-throughput screening for microarray data are rapidly developing and carry thepromiseofane?cient,cheap,andautomaticgatheringoftonsofhigh-quality data with large information potential. Thus, there is a need for appropriate - chine learning methods which help to automatically extract and interpret the relevant parts of this information and which, eventually, help to enable und- standingofbiologicalsystems,reliablediagnosisoffaults,andtherapyofdiseases such as cancer based on this information. Moreover, these application scenarios pose fundamental and qualitatively new challenges to the learning systems - cause of the speci?cs of the data and learning tasks. Since these characteristics are particularly pronounced within the medical domain, but not limited to it and of principled interest, this research topic opens the way toward important new directions of algorithmic design and accompanying theory.

This book contains 71 original, scienti?c articles that address state-of-the-art researchrelatedto scale space and variationalmethods for image processing and computer vision. Topics covered in the book range from mathematical analysis of both established and new models, fast numerical methods, image analysis, segmentation, registration, surface and shape construction and processing, to real applications in medical imaging and computer vision. The ideas of scale spaceandvariationalmethodsrelatedtopartialdi?erentialequationsarecentral concepts. The papers re?ect the newest developments in these ?elds and also point to the latest literature. All the papers were submitted to the Second International Conference on Scale Space and Variational Methods in Computer Vision, which took place in Voss, Norway, during June 1-5, 2009. The papers underwent a peer review process similar to that of high-level journals in the ?eld. We thank the authors, the Scienti?c Committee, the Program Committee and the reviewers for their hard work and helpful collaboration. Their contribution has been crucial for the e?cient processing of this book, and for the success of the conference.

This volume constitutes the refereed proceedings of the 4th Iberian Conference on Pattern Recognition and Image Analysis, IbPRIA 2009, held in Povoa de Varzim, Portugal in June 2009.

The 33 revised full papers and 29 revised poster papers presented together with 3 invited talks were carefully reviewed and selected from 106 submissions. The papers are organized in topical sections on computer vision, image analysis and processing, as well as pattern recognition.

This volume contains the papers presented at the 7th IAPR-TC-15 Workshop onGraph-BasedRepresentationsinPatternRecognition- GbR2009.Thewo- shop was held in Venice, Italy between May 26-28, 2009. The previous wo- shops in the series were held in Lyon, France (1997), Haindorf, Austria (1999), Ischia, Italy (2001), York, UK (2003), Poitiers, France (2005), and Alicante, Spain (2007). The Technical Committee (TC15, http: //www.greyc.ensicaen.fr/iapr-tc15/) of the IAPR (International Association for Pattern Recognition) was founded in order to federate and to encourage research work at the intersection of pattern recognition and graph theory. Among its activities, the TC15 encourages the organization of special graph sessions in many computer vision conferences and organizes the biennial GbR Workshop. The scienti?c focus of these workshops coversresearchin pattern recognition and image analysis within the graph theory framework. This workshop series traditionally provide a forum for presenting and discussing research results and applications in the intersection of pattern recognition, image analysis and graph theory

State-of-the-art technology and cutting-edge applications in image processing

Intelligent Image Processing examines the fundamentals of personal imaging and wearable computing with a concentration on the EyeTap technology invented by the author. EyeTap technology comprises eyeglasses or contact lenses that cause the eye itself to function, in effect, as if it were both a camera and a display. Modern embodiments of this invention use a laser system having no moving parts to provide infinite depth of focus from the inside of the eye, out to infinity. The invention eliminates the distinction between cyberspace and the real world, allowing a shared visual experience and shared visual memory among multiple users.

There are a wide range of commercial applications for this technology, including telephones that allow users to see each other’s points of view, and systems that improve the sight of the visually impaired. These systems have been proven for electronic news gathering in hostile environments such as fires, floods, riots, and documenting human rights violations–all giving rise to a new genre of first-person cinematography. The invention blurs the boundary between seeing and recording, and the boundary between computing and thinking. It will radically change the way pictures are taken, memories are shared, and news is documented.

The author approaches the fundamental ideas of wearable computing and personal imaging by providing an historical overview of the subject that takes the reader from his original wearable photographic computer inventions of the 1970s, through to the modern EyeTap system. This fascinating technology promises to change the way we live and the way we communicate, and Intelligent Image Processing provides a detailed, technical, and stimulating guide for those who wish to learn about or contribute to this promising future.

GeometricModelingandProcessing(GMP)isabiennialinternationalconference on geometric modeling, simulation and computing, which provides researchers and practitioners with a forum for exchanging new ideas, discussing new app- cations, and presenting new solutions. Previous GMP conferences were held in Pittsburgh (2006), Beijing (2004), Tokyo (2002), and Hong Kong (2000). This, the 5th GMP conference, was held in Hangzhou, one of the most beautiful cities in China. GMP 2008 received 113 paper submissions, covering a wide spectrum of - ometric modeling and processing, such as curves and surfaces, digital geometry processing, geometric feature modeling and recognition, geometric constraint solving, geometric optimization, multiresolution modeling, and applications in computer vision, image processing, scienti?c visualization, robotics and reverse engineering. Each paper was reviewed by at least three members of the program committee andexternalreviewers.Basedonthe recommendations ofthe revi- ers, 34 regular papers were selected for oral presentation, and 17 short papers were selected for poster presentation. All selected papers are included in these proceedings. We thank all authors, external reviewers and program committee members for their great e?ort and contributions, which made this conference a success.

Attention has represented a core scienti?c topic in the design of AI-enabled systems in the last few decades. Today, in the ongoing debate, design, and c- putationalmodelingofarti?cialcognitivesystems, attentionhasgainedacentral position as a focus of research. For instance, attentional methods are considered in investigating the interfacing of sensory and cognitive information processing, for the organization of behaviors, and for the understanding of individual and social cognition in infant development. Whilevisualcognitionplaysacentralroleinhumanperception, ?ndingsfrom neuroscience and experimental psychology have provided strong evidence about the perception-action nature of cognition. The embodied nature of senso- motor intelligence requires a continuous and focused interplay between the c- trolofmotoractivitiesandtheinterpretationoffeedbackfromperceptualmod- ities. Decision making about the selection of information from the incoming sensory stream - in tune with contextual processing on a current task and an agent's global objectives - becomes a further challenging issue in attentional control. Attention must operate at interfaces between a bottom-up-driven world interpretationandtop-down-driveninformationselection, thusactingatthecore of arti?cial cognitive systems. These insights have already induced changes in AI-related disciplines, such as the design of behavior-based robot control and the computational modeling of animats. Today, the development of enabling technologiessuch as autonomous robotic systems, miniaturizedmobile-evenwearable-sensors, andambientintelligence systems involves the real-time analysis of enormous quantities of data. These data have to be processed in an intelligent way to provide "on time delivery" of the required relevant information. Knowledge has to be applied about what needs to be attended to, and when, and what to do in a meaningful sequence, in correspondence with visual feedback.

This book contains the best papers of the Second International Conference on So- ware and Data Technologies (ICSOFT 2007), held in Barcelona, Spain. It was org- ized by the Institute for Systems and Technologies of Information, Communication and Control (INSTICC), co-sponsored by the Workflow Management Coalition (WfMC), in cooperation with the Interdisciplinary Institute for Collaboration and Research on Enterprise Systems and Technology (IICREST). The purpose of ICSOFT 2007 was to bring together researchers and practitioners int- ested in information technology and software development. The conference tracks were "Software Engineering," "Information Systems and Data Management," "Programming Languages," "Distributed and Parallel Systems" and "Knowledge Engineering." Being crucial for the development of information systems, software and data te- nologies encompass a large number of research topics and applications: from imp- mentation-related issues to more abstract theoretical aspects of software engineering; from databases and data warehouses to management information systems and kno- edge-base systems; next to that, distributed systems, pervasive computing, data quality and other related topics are included in the scope of this conference.

FromJune14-17,2008, theCenterforAdvancedGamingandSimulation(AGS), UtrechtUniversity, incollaborationwiththeNLGDFestivalofGames, organized a Workshop on Motion in Games in Utrecht. Motion plays a crucial role in c- puter games. Characters move around, objects are manipulated or move due to physical constraints, entities are animated, and the camera moves through the scene. Even the motion of the player nowadays is used as input to games. - tion is currently studied in many di?erent areas of research, including graphics and animation, gametechnology, robotics, simulation, computer vision, and also physics, psychology, and urban studies. The goal of the Motion in Games wo- shop was to bring together researchers from this variety of ?elds to present the most recent results and to initiate collaboration. TheMIG 2008workshophostedover30internationallyrenownedresearchers who all presentedtheir ongoingworkon topicssuch ascrowdsimulation, motion capture, path planning and facial animation. This volume is a collection of the paperspresentedduringthe workshop.Since this volumewaspublishedafterthe workshop, the authors of the papers adapted their content in order to include anydiscussionsthattookplaceduringtheworkshopitself.All?nalcontributions were carefully checked by the workshop organizers. The Motion in Games workshop was a very successful event that has set the starting point for interdisciplinary collaborations and for novel research ideas following the interesting discussions that took place. We are very happy with the outcomeofthe workshopandthe excellentcontributionsby the participants, collected in this volume. August 2008 Arjan Egges Arno Kamphuis Mark Overmars SponsoringInstitutions This workshop was sponsored by the GATE 1 2 project and the NLGD Festival of G

The automatic analysis of signals and images together with the characterization and elaboration of their representation features is still a challenging activity in many relevant scientific and hi-tech fields such as medicine, biotechnology, and chemistry. Multidimensional and multisource signal processing can generate a number of information patterns which can be useful to increase the knowledge of several domains for solving complex problems. Furthermore, advanced signal and image manipulation allows relating specific application problems into pattern recognition problems, often implying also the development of KDD and other computational intelligence procedures. Nevertheless, the amount of data produced by sensors and equipments used in biomedicine, biotechnology and chemistry is usually quite huge and structured, thus strongly pushing the need of investigating advanced models and efficient computational algorithms for automating mass analysis procedures. Accordingly, signal and image understanding approaches able to generate automatically expected outputs become more and more essential, including novel conceptual approaches and system architectures. The purpose of this third edition of the International Conference on Mass Data Analysis of Signals and Images in Medicine, Biotechnology, Chemistry and Food Industry (MDA 2008; www.mda-signals.de) was to present the broad and growing scientific evidence linking mass data analysis with challenging problems in medicine, biotechnology and chemistry. Scientific and engineering experts convened at the workshop to present the current understanding of image and signal processing and interpretation methods useful for facing various medical and biological problems and exploring the applicability and effectiveness of advanced techniques as solutions.

This book constitutes the refereed proceedings of the 9th International Conference on Advanced Concepts for Intelligent Vision Systems, ACIVS 2007, held in Delft, The Netherlands, August 28-31, 2007.

The 45 revised full papers and 55 revised poster papers presented were carefully reviewed and selected from around 221 submissions. The papers are organized in topical sections on noise reduction and restoration, segmentation, motion estimation and tracking, video processing and coding, camera calibration, image registration and stereo matching, biometrics and security, medical imaging, image retrieval and image understanding, as well as classification and recognition.

This book constitutes the refereed proceedings of the 6th International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition, EMMCVPR 2007, held in Ezhou, China in August 2007.

The 22 revised full papers and 15 poster papers presented were carefully reviewed and selected from 140 submissions. The papers are organized in topical sections on algorithms, applications, image parsing, image processing, motion, shape, and three-dimensional processing.