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 were able 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

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 were able 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 contains refereed and improved papers presented at the Seventh IAPR Workshop on Graphics Recognition (GREC2007), held in Curitiba, Brazil, September 20-21, 2007. The GREC workshops provide an excellent opportunity for researchers and practitioners at all levels of experience to meet colleagues and to share new ideas and knowledge about graphics recognition methods. Graphics recognition is a subfield of document image analysis that deals with graphical entities in engineering drawings, sketches, maps, architectural plans, musical scores, mathematical notation, tables, diagrams, etc. GREC2007 continued the tradition of past workshops held at Penn State University, USA (GREC 1995, LNCS Volume 1072, Springer, 1996); Nancy, France (GREC 1997, LNCS Volume 1389, Springer, 1998); Jaipur, India (GREC 1999, LNCS Volume 1941, Springer, 2000); Kingston, Canada (GREC 2001, LNCS Volume 2390, Springer, 2002); Barcelona, Spain (GREC 2003, LNCS Volume 3088, Springer, 2004); and Hong Kong, China (GREC 2005, LNCS Volume 3926, Springer, 2006). GREC2007 was also the first edition of a GREC workshop held at the same location of the ICDAR conference and it facilitated people to attend to both events. The program of GREC2007 was organized in a single-track 2-day workshop. It comprised several sessions dedicated to specific topics.

Affect and emotion play an important role in our everyday lives: They are present whatever we do, wherever we are, and wherever we go, without us being aware of them for much of the time. When it comes to interaction, be it with humans, technology, or humans via technology, we suddenly become more aware of emotion, either by seeing the other's emotional expression, or by not getting an emotional response while anticipating one.

Given this, it seems only sensible to explore affect and emotion in human-computer interaction, to investigate the underlying principles, to study the role they play, to develop methods to quantify them, and to finally build applications that make use of them. This is the research field for which, over ten years ago, Rosalind Picard coined the phrase "affective computing."

The present book provides an account of the latest work on a variety of aspects related to affect and emotion in human-technology interaction. It covers theoretical issues, user experience and design aspects as well as sensing issues, and reports on a number of affective applications that have been developed in recent years.

This book constitutes the refereed proceedings of the 7th International Workshop on Multiple Classifier Systems, MCS 2007, held in Prague, Czech Republic in May 2007.

The 49 revised full papers presented together with 2 invited papers were carefully reviewed and selected from more than 80 initial submissions. The papers are organized in topical sections on kernel-based fusion, applications, boosting, cluster and graph ensembles, feature subspace ensembles, multiple classifier system theory, intramodal and multimodal fusion of biometric experts, majority voting, and ensemble learning.

ICDM / MLDM Medaillie (limited edition) Meissner Porcellan, the "White Gold" of King August the Strongest of Saxonia ICDM 2008 was the eighth event of the Industrial Conference on Data Mining held in Leipzig (www.data-mining-forum.de). For this edition the Program Committee received 116 submissions from 20 countries. After the peer-review process, we accepted 36 high-quality papers for oral presentation, which are included in these proceedings. The topics range from aspects of classification and prediction, clustering, Web mining, data mining in medicine, applications of data mining, time series and frequent pattern mining, and association rule mining. Thirteen papers were selected for poster presentations that are published in the ICDM Poster Proceeding Volume. In conjunction with ICDM there were three workshops focusing on special hot application-oriented topics in data mining. The workshop Data Mining in Life Science DMLS 2008 was held the third time this year and the workshop Data Mining in Marketing DMM 2008 ran for the second time this year. Additionally, we introduced an International Workshop on Case-Based Reasoning for Multimedia Data CBR-MD.

This volume (5116) of Springer's Lecture Notes in Computer Science contains the th proceedings of the 9 International Workshop on Digital Mammography (IWDM) which was held July 20 - 23, 2008 in Tucson, AZ in the USA. The IWDM meetings traditionally bring together a diverse set of researchers (physicists, mathematicians, computer scientists, engineers), clinicians (radiologists, surgeons) and representatives of industry, who are jointly committed to developing technologies to support clinicians in the early detection and subsequent patient management of breast cancer. The IWDM conference series was initiated at a 1993 meeting of the SPIE Medical Imaging Symposium in San Jose, CA, with subsequent meetings hosted every two years at sites around the world. Previous meetings were held in York, England; Chicago, IL USA; Nijmegen, Netherlands; Toronto, Canada; Bremen, Germany; Durham, NC USA and Manchester, UK. th The 9 IWDM meeting was attended by a very international group of participants, and during the two and one-half days of scientific sessions there were 70 oral presentations, 34 posters and 3 keynote addresses. The three keynote speakers discussed some of the "hot" topics in breast imaging today. Karen Lindfors spoke on "Dedicated Breast CT: Initial Clinical Experiences. " Elizabeth Rafferty asked the question is "Breast Tomosynthesis: Ready for Prime Time?" Finally, Martin Tornai discussed "3D Multi-Modality Molecular Breast Imaging.

TheThirdIAPRTC3WorkshoponArti?cialNeuralNetworksinPatternRec- nition, ANNPR 2008, was held at Pierre and Marie Curie University in Paris (France), July 2-4, 2008. The workshop was organized by the Technical C- mittee on Neural Networks and Computational Intelligence (TC3) that is one of the 20 TCs of the International Association for Pattern Recognition (IAPR). The scope of TC3 includes computational intelligence approaches, such as fuzzy systems, evolutionary computing and arti?cial neural networks and their use in various pattern recognition applications. ANNPR 2008 followed the success of the previous workshops: ANNPR 2003 held at the University of Florence (Italy) andANPPR 2006held at ReisensburgCastle, Universityof Ulm (Germany).All the workshops featured a single-track program including both oral sessions and posters with a focus on active participation from every participant. Inrecentyears, the?eld ofneuralnetworkshasmaturedconsiderablyinboth methodologyandreal-worldapplications.Asre?ectedinthisbook, arti?cialn- ral networks in pattern recognition combine many ideas from machine learning, advanced statistics, signal and image processing for solving complex real-world pattern recognition problems. High quality across such a diverse ?eld of research can only be achieved through a rigorous and selective review process. For this workshop, 57 papers were submitted out of which 29 were selected for inclusion in the proceedings. The oral sessions included 18 papers, while 11 contributions were presented as posters. ANNPR 2008 featured research works in the areas of supervised and unsupervised learning, multiple classi?er systems, pattern recognition in signal and image processing, and feature selectio

This year, 2008, we had a very special Annual Symposium of the Deutsche Arbeitsgemeinschaft fur ] Mustererkennung (DAGM) in Munich, and there are several reasons for that. First ofall, this yearwasthe 30th anniversaryof the symposium. Thismeans that the ?rst symposium was organized in 1978 and the location of this event was: Munich Justtwoyearsbefore, in1976, theDAGMwasfoundedin: Munich And Munich was also the location of two further DAGM symposia, in 1991 and in 2001. When I attended the conference in 2001, I was in negotiations for my appointmentto the Chair ofHuman-MachineCommunicationatthe Technische Universit] atMunc ] hen(TUM)andcertainlyIdidnotatallanticipatethatIwould have the pleasure and honor to host this conference just seven years later again in Munich for its 30th anniversary. But special dates are not the only reason why DAGM was somewhat di?- ent this time. This year, DAGM was organized in conjunction with Automatica, the Third International Trade Fair for Automation in Assembly, Robotics, and Vision, one of the world's leading fairs in automation and robotics. This was an ideal platform for the exchange of ideas and people between the symposium and the fair, and the conference thus took place in a somewhat unusual but extra- dinary location, the International Congress Center (ICM), in the direct vicinity of the New Munich Trade Fair Center, the location of the Automatica fair. With free access to Automatica, the registrants of DAGM got the opportunity to make full use of all the synergy e?ects associated with this special arrangement."

The papers contained in this volume were presented at the 19th Annual S- posium on Combinatorial Pattern Matching (CPM 2008) held at the University of Pisa, Italy, June 18-20, 2008. All the papers presented at the conference are originalresearchcontributions on computational pattern matching and analysis. They were selected from 78 submissions. Each submission was reviewed by at least three reviewers. The committee decided to accept 25 papers. The programme also includes three invited talks by Daniel M. Gus?eld from the University of California, Davis, USA, J. Ian Munro from the University of Waterloo, Canada, and Prabhakar Raghavan from Yahoo! Research, USA. The objective of the annual CPM meetings is to provide an international forum for research in combinatorial pattern matching and related applications. It addresses issues of searching and matching strings and more complicated p- terns such as trees, regular expressions, graphs, point sets, and arrays. The goal is to derive non-trivialcombinatorialproperties of suchstructures and to exploit these properties in order to either achieve superior performance for the cor- sponding computational problems or pinpoint conditions under which searches cannotbeperformede?ciently. Themeeting also dealswith problems incom- tational biology, data compression, data mining, coding, information retrieval, natural language processing and pattern recognition.

The two volume set LNCS 4291 and LNCS 4292 constitutes the refereed proceedings of the Second International Symposium on Visual Computing, ISVC 2006, held in Lake Tahoe, NV, USA in November 2006.

The 65 revised full papers and 56 poster papers presented together with 57 papers of ten special tracks were carefully reviewed and selected from more than 280 submissions. The papers cover the four main areas of visual computing.

As well as conveying a message in words and sounds, the speech signal carries information about the speaker's own anatomy, physiology, linguistic experience and mental state. These speaker characteristics are found in speech at all levels of description: from the spectral information in the sounds to the choice of words and utterances themselves.

This two volume set, LNAI 4343 and LNAI 4441, constitutes a state-of-the-art survey for the field of speaker classification. It approaches the following questions: What characteristics of the speaker become manifest in his or her voice and speaking behavior? Which of them can be inferred from analyzing the acoustic realizations? What can this information be used for? Which methods are the most suitable for diversified problems in this area of research? How should the quality of the results be evaluated?

The 22 articles of the second volume comprise a number of selected self-contained papers on research projects in the field of speaker classification. These include among other things a report on a gender recognition system; a study on emotion recognition; a presentation of a text-dependent speaker verification system; an account of the analysis of both speaker and verbal content information - as well as studies on accent identification.

The two volume set LNCS 4141, and LNCS 4142 constitute the refereed proceedings of the Third International Conference on Image Analysis and Recognition, ICIAR 2006, held in Povoa de Varzim, Portugal in September 2006.

The 71 revised full papers and 92 revised poster papers presented together with 2 invited lectures were carefully reviewed and selected from 389 submissions. The papers are organized in topical sections on image restoration and enhancement, image segmentation, image and video processing and analysis, image and video coding and encryption, image retrieval and indexing, motion analysis, and tracking in the first volume. The second volume contains topical sections on pattern recognition for image analysis, computer vision, biometrics, shape and matching, biomedical image analysis, brain imaging, remote sensing image processing, and applications.

This book constitutes the refereed proceedings of the Third International Workshop on Analysis and Modelling of Faces and Gestures, AMFG 2007, held in Rio de Janeiro, Brazil, in October 2007 within the scope of ICCV 2007, the International Conference on Computer Vision.

The 8 revised full papers presented together with 13 revised poster papers were carefully reviewed and selected from 55 submissions. The papers review the status of recognition, analysis and modeling of face, gesture, activity, and behavior. Topics addressed include feature representation, 3D face, robust recognition under pose and illumination variations, video-based face recognition, learning, facial motion analysis, body pose estimation, and sign recognition.

This book constitutes the thoroughly refereed post-proceedings of the 9th International Conference on Visual Information Systems, VISUAL 2007, held in Shanghai, China, in June 2007.

The 54 revised full papers presented together with 1 keynote lecture were carefully reviewed and selected from 117 submissions. The papers are organized in topical section on image and video retrieval, visual biometrics, intelligent visual information processing, visual data mining, ubiquitous and mobile visual information systems, semantics, 2D/3D graphical visual data retrieval, and applications of visual information systems.

This book constitutes the refereed proceedings of the Second International Conference on Pattern Recognition and Machine Intelligence, PReMI 2007, held in Kolkata, India in December 2007.

The 82 revised papers presented were carefully reviewed and selected from 241 submissions. The papers are organized in topical sections on pattern recognition, image analysis, soft computing and applications, data mining and knowledge discovery, bioinformatics, signal and speech processing, document analysis and text mining, biometrics, and video analysis.

This book constitutes the refereed proceedings of the 17th Annual Symposium on Combinatorial Pattern Matching, CPM 2006, held in Barcelona, Spain, July 2006. The book presents 33 revised full papers together with 3 invited talks, organized in topical sections on data structures, indexing data structures, probabilistic and algebraic techniques, applications in molecular biology, string matching, data compression, and dynamic programming.

This book constitutes the thoroughly refereed post-proceedings of the 6th International Workshop on Graphics Recognition, GREC 2005, held in Hong Kong, China, August 2005. The book presents 37 revised full papers together with a panel discussion report, organized in topical sections on engineering drawings vectorization and recognition, symbol recognition, graphic image analysis, structural document analysis, sketching and online graphics recognition, curves and shape processing, and graphics recognition contest results.

This book constitutes the refereed proceedings of the 29th Symposium of the German Association for Pattern Recognition, DAGM 2007, held in Heidelberg Germany in September 2007.

The 55 revised full papers were carefully reviewed and selected. The papers are organized in topical sections on image filtering, restoration and segmentation, shape analysis and representation, recognition, categorization and detection, computer vision and image retrieval, machine learning and statistical data analysis, biomedical data analysis, motion analysis and tracking, pose recognition, stereo and structure from motion, multi-view image and geometric processing, as well as 3D view registration and surface modelling.

This book constitutes the refereed proceedings of the 12th International Conference on Computer Analysis of Images and Patterns, CAIP 2007, held in Vienna, Austria, in August 2007.

The 120 revised full papers presented together with 3 invited lectures were carefully reviewed and selected from 251 submissions. The papers are organized in topical sections on motion detection and tracking, medical imaging, biometrics, colour, curves and surfaces beyond two dimensions, reading characters, words, lines etc., image segmentation, shape, im age registration and matching, signal decomposition and invariants, as well as features and classification.

This book constitutes the refereed proceedings of the 6th IAPR-TC-15 International Workshop on Graph-Based Representations in Pattern Recognition, GbRPR 2007, held in Alicante, Spain in June 2007.

The 23 revised full papers and 14 revised poster papers presented were carefully reviewed and selected from 54 submissions. The papers are organized in topical sections on matching, distances and measures, graph-based segmentation and image processing, graph-based clustering, graph representations, pyramids, combinatorial maps and homologies, as well as graph clustering, embedding and learning.

The two-volume set LNCS 4477 and 4478 constitutes the refereed proceedings of the Third Iberian Conference on Pattern Recognition and Image Analysis, IbPRIA 2007, held in Girona, Spain in June 2007.

The 48 revised full papers and 108 revised poster papers presented together with 3 invited talks were carefully reviewed and selected from 328 submissions. The papers are organized in topical sections on pattern recognition, human language technology, special architectures and industrial applications, motion analysis, image analysis, biomedical applications, shape and texture analysis, 3D, as well as image coding and processing.

Although research in computer vision for recognizing 3D objects in photographs dates back to the 1960s, progress was relatively slow until the turn of the millennium, and only now do we see the emergence of effective techniques for recognizing object categories with different appearances under large variations in the observation conditions. Tremendous progress has been achieved in the past five years, thanks largely to the integration of new data representations, such as invariant semi-local features, developed in the computer vision community with the effective models of data distribution and classification procedures developed in the statistical machine-learning community.

This volume is a post-event proceedings volume and contains selected papers based on presentations given, and vivid discussions held, during two workshops held in Taormina in 2003 and 2004. The main goals of these two workshops were to promote the creation of an international object recognition community, with common datasets and evaluation procedures, to map the state of the art and identify the main open problems and opportunities for synergistic research, and to articulate the industrial and societal needs and opportunities for object recognition research worldwide.

The 30 thoroughly revised papers presented are organized in the following topical sections: recognition of specific objects, recognition of object categories, recognition of object categories with geometric relations, and joint recognition and segmentation.

This book constitutes the thoroughly refereed post-proceedings of the First International Workshop on Spatial Coherence for Visual Motion Analysis, 2004, held in May 2004. The eleven revised full research papers presented went through two rounds of reviewing and improvement. The papers in this volume cover a wide range in the field of motion analysis that is a central problem in computer vision. The workshop examined techniques for integrating spatial coherence constraints during motion analysis of image sequences.

This book constitutes the refereed proceedings of the 18th Annual Symposium on Combinatorial Pattern Matching, CPM 2007, held in London, Canada in July 2007.

The 32 revised full papers presented together with 3 invited talks were carefully reviewed and selected from 64 submissions. The papers are organized in topical sections on algorithmic techniques, approximate pattern matching, data compression, computational biology, pattern analysis, suffix arrays and trees, as well as algorithmic techniques.