IbPRIA 2005 (Iberian Conference on Pattern Recognition and Image Analysis) was the second of a series of conferences jointly organized every two years by the Portuguese and Spanish Associations for Pattern Recognition (APRP, AERFAI), with the support of the International Association for Pattern Recognition (IAPR). This year, IbPRIA was hosted by the Institute for Systems and Robotics and the Geo-systems Center of the Instituto Superior Tecn ico and it was held in Estoril, Por- gal. It provided the opportunity to bring together researchers from all over the world to discuss some of the most recent advances in pattern recognition and all areas of video, image and signal processing. There was a very positive response to the Call for Papers for IbPRIA 2005. We - ceived 292 full papers from 38 countries and 170 were accepted for presentation at the conference. The high quality of the scienti?c program of IbPRIA 2005 was due ?rst to the authors who submitted excellent contributions and second to the dedicated colla- ration of the international Program Committee and the other researchers who reviewed the papers. Each paper was reviewed by two reviewers, in a blind process. We would like to thank all the authors for submitting their contributions and for sharing their - search activities. We are particularly indebted to the Program Committee members and to all the reviewers for their precious evaluations, which permitted us to set up this publication."

This book and its sister volumes constitute the proceedings of the 2nd International Symposium on Neural Networks (ISNN 2005). ISNN 2005 was held in the beautiful mountain city Chongqing by the upper Yangtze River in southwestern China during May 30-June 1, 2005, as a sequel of ISNN 2004 successfully held in Dalian, China. ISNN emerged as a leading conference on neural computation in the region with - creasing global recognition and impact. ISNN 2005 received 1425 submissions from authors on ?ve continents (Asia, Europe, North America, South America, and Oc- nia), 33 countries and regions (Mainland China, Hong Kong, Macao, Taiwan, South Korea, Japan, Singapore, Thailand, India, Nepal, Iran, Qatar, United Arab Emirates, Turkey, Lithuania, Hungary, Poland, Austria, Switzerland, Germany, France, Sweden, Norway, Spain, Portugal, UK, USA, Canada, Venezuela, Brazil, Chile, Australia, and New Zealand). Based on rigorous reviews, 483 high-quality papers were selected by the Program Committee for presentation at ISNN 2005 and publication in the proce- ings, with an acceptance rate of less than 34%. In addition to the numerous contributed papers, 10 distinguished scholars were invited to give plenary speeches and tutorials at ISNN 2005.

E-commerce services are su?ering abuse by programs (bots, spiders, etc.) m- querading as legitimate human users. E?orts to defend against such attacks have, over the past several years, stimulated investigations into a new family of security protocols - "Human Interactive Proofs" (HIPs) - which allow a person to authenticate herself as a member of a given group: e.g., as a human (vs. a machine), as herself (vs. anyoneelse), as an adult (vs. a child). Most commercial usesofHIPstodayareCAPTCHAs,"CompletelyAutomaticPublicTuringtests to tell Computers and Humans Apart," which exploit the gap in ability between humans and machine vision systems in reading images of text. HIP challenges can also be non-graphical, e.g., requiring recognition of speech, solving puzzles, etc. Wearepleasedtopresentthe?rstrefereedandarchivallypublishedcollection of state-of-the-art papers on HIPs and CAPTCHAs. Each paper was reviewed by three members of the Program Committee, judged by the Co-chairs to be of su?cient relevance and quality, and revised by the authors in response to the referees' suggestions. The papers investigate performance analysis of novel CAPTCHAs, HIP - chitectures, and the role of HIPs within security systems. Kumar Chellapilla, Kevin Larson, Patrice Simard, and Mary Czerwinski describe user trials of a CAPTCHA designed to resist segmentation attacks, including a systematic evaluation of its tolerance by human users. Henry Baird, Michael Moll, and Sui- Yu Wang analyze data from a human legibility trial of another segmentati- resistantCAPTCHAandlocateahighlylegibleengineeringregime.AmaliaRusu and Venu Govindaraju describe research towards CAPTCHAs based on reading synthetically damaged images of real images of unconstrained handwritten text.

The three volume set LNCS 3496/3497/3498 constitutes the refereed proceedings of the Second International Symposium on Neural Networks, ISNN 2005, held in Chongqing, China in May/June 2005.

The 483 revised papers presented were carefully reviewed and selected from 1.425 submissions. The papers are organized in topical sections on theoretical analysis, model design, learning methods, optimization methods, kernel methods, component analysis, pattern analysis, systems modeling, signal processing, image processing, financial analysis, control systems, robotic systems, telecommunication networks, incidence detection, fault diagnosis, power systems, biomedical applications, industrial applications, and other applications.

The three volume set LNCS 3496/3497/3498 constitutes the refereed proceedings of the Second International Symposium on Neural Networks, ISNN 2005, held in Chongqing, China in May/June 2005.

The 483 revised papers presented were carefully reviewed and selected from 1.425 submissions. The papers are organized in topical sections on theoretical analysis, model design, learning methods, optimization methods, kernel methods, component analysis, pattern analysis, systems modeling, signal processing, image processing, financial analysis, control systems, robotic systems, telecommunication networks, incidence detection, fault diagnosis, power systems, biomedical applications, industrial applications, and other applications.

Fuzzy Models and Algorithms for Pattern Recognition and Image Processing presents a comprehensive introduction of the use of fuzzy models in pattern recognition and selected topics in image processing and computer vision. Unique to this volume in the Kluwer Handbooks of Fuzzy Sets Series is the fact that this book was written in its entirety by its four authors. A single notation, presentation style, and purpose are used throughout. The result is an extensive unified treatment of many fuzzy models for pattern recognition. The main topics are clustering and classifier design, with extensive material on feature analysis relational clustering, image processing and computer vision. Also included are numerous figures, images and numerical examples that illustrate the use of various models involving applications in medicine, character and word recognition, remote sensing, military image analysis, and industrial engineering.

Many vision problems have to deal with di?erent entities (regions, lines, line junctions, etc.) and their relationships. These entities together with their re- tionships may be encoded using graphs or hypergraphs. The structural inf- mation encoded by graphs allows computer vision algorithms to address both the features of the di?erent entities and the structural or topological relati- ships between them. Moreover, turning a computer vision problem into a graph problem allows one to access the full arsenal of graph algorithms developed in computer science. The Technical Committee (TC15, http: //www.iapr.org/tcs.html) of the IAPR (International Association for Pattern Recognition) has been funded in order to federate and to encourage research work in these ?elds. Among its - tivities, TC15 encourages the organization of special graph sessions at many computer vision conferences and organizes the biennial workshop GbR. While being designed within a speci?c framework, the graph algorithms developed for computer vision and pattern recognition tasks often share constraints and goals with those developed in other research ?elds such as data mining, robotics and discrete geometry. The TC15 community is thus not closed in its research ?elds but on the contrary is open to interchanges with other groups/communities

In this volume we present the contributions for the 18th European Conference on Genetic Programming (EuroGP 2005). The conference took place from 30 March to 1 April in Lausanne, Switzerland. EuroGP is a well-established conf- ence and the only one exclusively devoted to genetic programming. All previous proceedings were published by Springer in the LNCS series. From the outset, EuroGP has been co-located with the EvoWorkshops focusing on applications of evolutionary computation. Since 2004, EvoCOP, the conference on evolutionary combinatorial optimization, has also been co-located with EuroGP, making this year's combined events one of the largest dedicated to evolutionary computation in Europe. Genetic programming (GP) is evolutionary computation that solves complex problems or tasks by evolving and adapting a population of computer programs, using Darwinian evolution and Mendelian genetics as its sources of inspiration. Some of the 34 papers included in these proceedings address foundational and theoretical issues and there is also a wide variety of papers dealing with di?erent application areas, such as computer science, engineering, language processing, biology and computational design, demonstrating that GP is a powerful and practical problem-solving paradigm.

Biometric Systems provides practitioners with an overview of the principles and methods needed to build reliable biometric systems. It covers three main topics: key biometric technologies, design and management issues, and the performance evaluation of biometric systems for personal verification/identification. The four most widely used technologies are focused on - speech, fingerprint, iris and face recognition.

Key features include: in-depth coverage of the technical and practical obstacles which are often neglected by application developers and system integrators and which result in shortfalls between expected and actual performance; and protocols and benchmarks which will allow developers to compare performance and track system improvements.

The 2nd International Workshop on Statistical Methods in Video Processing, SMVP 2004, was held in Prague, Czech Republic, as an associated workshop of ECCV 2004, the 8th European Conference on Computer Vision. A total of 30 papers were submitted to the workshop. Of these, 17 papers were accepted for presentation and included in these proceedings, following a double-blind review process. The workshop had 42 registered participants. The focus of the meeting was on recent progress in the application of - vanced statistical methods to solve computer vision tasks. The one-day scienti?c program covered areas of high interest in vision research, such as dense rec- struction of 3D scenes, multibody motion segmentation, 3D shape inference, errors-in-variables estimation, probabilistic tracking, information fusion, optical ?owcomputation, learningfornonstationaryvideodata, noveltydetectionin- namic backgrounds, background modeling, grouping using feature uncertainty, and crowd segmentation from video. We wish to thank the authors of all submitted papers for their interest in the workshop.Wealsowishtothankthemembersofourprogramcommitteeandthe external reviewers for their commitment of time and e?ort in providing valuable recommendations for each submission. We are thankful to Vaclav Hlavac, the General Chair of ECCV 2004, and to Radim Sara, for the local organization of the workshop and registration management. We hope you will ?nd these proceedings both inspiring and of high scienti?c qualit

Following the previous four annual conferences, the 5th Chinese Conference on Biometrics Recognition (Sinobiometrics 2004) was held in Guangzhou, China in December 2004. The conference this year was aimed at promoting the international exchange of ideas and providing an opportunity for keeping abreast of the latest developments in biometric algorithms, systems, and applications. The 1st Biometrics Verification Competition (BVC) on face, iris, and fingerprint recognition was also conducted in conjunction with the conference. This book is composed of 74 papers presented at Sinobiometrics 2004, contributed by researchers and industrial practitioners from Korea, Japan, Singapore, Hong Kong, France, UK, US, as well as China. Of these, 60 papers were selected from 140 submissions and 14 were invited. The papers not only presented recent technical advances, but also addressed issues in biometric system design, standardization, and applications. Included among the invited were four feature papers on the ideas and algorithms of the best-performing biometric engines, which were either competition winners at the Face Authentication Test (FAT) 2004 or the Fingerprint Verification Competition (FVC) 2004, or they were the best-performing iris and palmprint recognition algorithms. The papers were complemented by five keynote lectures on biometrics, and face, fingerprint, and iris authentication and multimodal fusion by Arun Ross (West Virginia University) and Anil K. Jain (Michigan State University), Josef Kittler (University of Surrey), John Daugman (University of Cambridge), Raffaele Cappelli (University of Bologna), and Stan Z. Li (Chinese Academy of Sciences).

First of all, we want to congratulate two new research communities from M- ico and Brazil that have recently joined the Iberoamerican community and the International Association for Pattern Recognition. We believe that the series of congresses that started as the "Taller Iberoamericano de Reconocimiento de Patrones (TIARP)," and later became the "Iberoamerican Congress on Pattern Recognition (CIARP)," has contributed to these groupconsolidatione?orts. We hope that in the near future all the Iberoamerican countries will have their own groups and associations to promote our areas of interest; and that these congresses will serve as the forum for scienti?c research exchange, sharing of - pertise and new knowledge, and establishing contacts that improve cooperation between research groups in pattern recognition and related areas. CIARP 2004 (9th Iberoamerican Congress on Pattern Recognition) was the ninthinaseriesofpioneeringcongressesonpatternrecognitionintheIberoam- ican community. As in the previous year, CIARP 2004 also included worldwide participation. It took place in Puebla, Mexico. The aim of the congress was to promote and disseminate ongoing research and mathematical methods for pattern recognition, image analysis, and applications in such diverse areas as computer vision, robotics, industry, health, entertainment, space exploration, telecommunications, data mining, document analysis, and natural languagep- cessing and recognition, to name a few.

1 Thisbookcontainsrefereedandimprovedpaperspresentedatthe5thIAPR - ternational Workshop on Graphics Recognition (GREC 2003). GREC 2003 was held in the Computer Vision Center, in Barcelona (Spain) during July 30-31, 2003. TheGRECworkshopisthemainactivityoftheIAPR-TC10, theTechnical 2 Committee on Graphics Recognition . Edited volumes from the previous wo- shops in the series are available as Lecture Notes in Computer Science: LNCS Volume 1072 (GREC 1995 at Penn State University, USA), LNCS Volume 1389 (GREC 1997 in Nancy, France), LNCS Volume 1941 (GREC 1999 in Jaipur, India), and LNCS Volume 2390 (GREC 2001 in Kingston, Canada). Graphics recognition is a particular ?eld in the domain of document ana- sis that combines pattern recognition and image processing techniques for the analysis of any kind of graphical information in documents, either from paper or electronic formats. Topics of interest for the graphics recognition community are: vectorization; symbol recognition; analysis of graphic documents with - agrammatic notation like electrical diagrams, architectural plans, engineering drawings, musical scores, maps, etc.; graphics-based information retrieval; p- formance evaluation in graphics recognition; and systems for graphics recog- tion. Inadditiontotheclassicobjectives, inrecentyearsgraphicsrecognitionhas faced up to new and promising perspectives, some of them in conjunction with other, a?ne scienti?c communities. Examples of that are sketchy interfaces and on-line graphics recognition in the framework of human computer interaction, or query by graphic content for retrieval and browsing in large-format graphic d- uments, digital libraries and Web applications. Thus, the combination of classic challenges with new research interests gives the graphics recognition ?eld an active scienti?c community, with a promising future

ICIAR 2004, the International Conference on Image Analysis and Recognition, was the ?rst ICIAR conference, and was held in Porto, Portugal. ICIAR will be organized annually, and will alternate between Europe and North America. ICIAR 2005 will take place in Toronto, Ontario, Canada. The idea of o?ering these conferences came as a result of discussion between researchers in Portugal and Canada to encourage collaboration and exchange, mainly between these two countries, but also with the open participation of other countries, addressing recent advances in theory, methodology and applications. The response to the call for papers for ICIAR 2004 was very positive. From 316 full papers submitted, 210 were accepted (97 oral presentations, and 113 - sters). The review process was carried out by the Program Committee members and other reviewers; all are experts in various image analysis and recognition areas. Each paper was reviewed by at least two reviewing parties. The high q- lity of the papers in these proceedings is attributed ?rst to the authors, and second to the quality of the reviews provided by the experts. We would like to thank the authors for responding to our call, and we wholeheartedly thank the reviewers for their excellent work in such a short amount of time. We are espe- ally indebted to the Program Committee for their e?orts that allowed us to set up this publication. We were very pleased to be able to include in the conference, Prof. Murat KuntfromtheSwissFederalInstituteofTechnology, andProf. Mario Figueiredo, oftheInstitutoSuperiorT ecnico, inPortugal."

ICIAR 2004, the International Conference on Image Analysis and Recognition, was the ?rst ICIAR conference, and was held in Porto, Portugal. ICIAR will be organized annually, and will alternate between Europe and North America. ICIAR 2005 will take place in Toronto, Ontario, Canada. The idea of o?ering these conferences came as a result of discussion between researchers in Portugal and Canada to encourage collaboration and exchange, mainly between these two countries, but also with the open participation of other countries, addressing recent advances in theory, methodology and applications. The response to the call for papers for ICIAR 2004 was very positive. From 316 full papers submitted, 210 were accepted (97 oral presentations, and 113 - sters). The review process was carried out by the Program Committee members and other reviewers; all are experts in various image analysis and recognition areas. Each paper was reviewed by at least two reviewing parties. The high q- lity of the papers in these proceedings is attributed ?rst to the authors, and second to the quality of the reviews provided by the experts. We would like to thank the authors for responding to our call, and we wholeheartedly thank the reviewers for their excellent work in such a short amount of time. We are espe- ally indebted to the Program Committee for their e?orts that allowed us to set up this publication. We were very pleased to be able to include in the conference, Prof. Murat KuntfromtheSwissFederalInstituteofTechnology, andProf. Mario Figueiredo, oftheInstitutoSuperiorT ecnico, inPortugal."

Machine Learning has become a key enabling technology for many engineering applications, investigating scientific questions and theoretical problems alike. To stimulate discussions and to disseminate new results, a summer school series was started in February 2002, the documentation of which is published as LNAI 2600.

This book presents revised lectures of two subsequent summer schools held in 2003 in Canberra, Australia, and in T bingen, Germany. The tutorial lectures included are devoted to statistical learning theory, unsupervised learning, Bayesian inference, and applications in pattern recognition; they provide in-depth overviews of exciting new developments and contain a large number of references.

Graduate students, lecturers, researchers and professionals alike will find this book a useful resource in learning and teaching machine learning.

Thisvolumecontainspapersselectedforpresentationatthe6thIAPRWorkshop on Document Analysis Systems (DAS 2004) held during September 8-10, 2004 at the University of Florence, Italy. Several papers represent the state of the art in a broad range of "traditional" topics such as layout analysis, applications to graphics recognition, and handwritten documents. Other contributions address the description of complete working systems, which is one of the strengths of this workshop. Some papers extend the application domains to other media, like the processing of Internet documents. The peculiarity of this 6th workshop was the large number of papers related to digital libraries and to the processing of historical documents, a taste which frequently requires the analysis of color documents. A total of 17 papers are associated with these topics, whereas two yearsago (in DAS 2002) only a couple of papers dealt with these problems. In our view there are three main reasons for this new wave in the DAS community. From the scienti?c point of view, several research ?elds reached a thorough knowledge of techniques and problems that can be e?ectively solved, and this expertise can now be applied to new domains. Another incentive has been provided by several research projects funded by the EC and the NSF on topics related to digital libraries.

We are delighted to present the proceedings of DAGM 2004, and wish to - press our gratitude to the many people whose e?orts made the success of the conference possible. We received 146 contributions of which we were able to - cept 22 as oral presentations and 48 as posters. Each paper received 3 reviews, upon which decisions were based. We are grateful for the dedicated work of the 38 members of the program committee and the numerous referees. The careful review process led to the exciting program which we are able to present in this volume. Among the highlights of the meeting were the talks of our four invited spe- ers, renowned experts in areas spanning learning in theory, in vision and in robotics: - William T. Freeman, Arti?cial Intelligence Laboratory, MIT: Sharing F- tures for Multi-class Object Detection - PietroPerona,Caltech:TowardsUnsupervisedLearningofObjectCategories - StefanSchaal,DepartmentofComputerScience,UniversityofSouthernC- ifornia: Real-Time Statistical Learning for Humanoid Robotics - Vladimir Vapnik, NEC Research Institute: Empirical Inference WearegratefulforeconomicsupportfromHondaResearchInstituteEurope, ABW GmbH, Transtec AG, DaimlerChrysler, and Stemmer Imaging GmbH, which enabled us to ? nance best paper prizes and a limited number of travel grants. Many thanks to our local support Sabrina Nielebock and Dagmar Maier, who dealt with the unimaginably diverse range of practical tasks involved in planning a DAGM symposium. Thanks to Richard van de Stadt for providing excellent software and support for handling the reviewing process. A special thanks goes to Jeremy Hill, who wrote and maintained the conference website.

This volume contains all papers presented at SSPR 2004 and SPR 2004, hosted by the Instituto de Telecomunicac" ,oes/Instituto Superior T' ecnico, Lisbon, Portugal, August 18-20, 2004. This was the fourth time that the two workshops were held back-to-back. The SSPR was the tenth International Workshop on Structural and Synt- tic Pattern Recognition, and the SPR was the ?fth International Workshop on Statistical Techniques in Pattern Recognition. These workshops have traditi- ally been held in conjunction with ICPR (International Conference on Pattern Recognition), and are the major events for technical committees TC2 and TC1, respectively, of the International Association for Pattern Recognition (IAPR). The workshops were closely coordinated, being held in parallel, with plenary talks and a common session on hybrid systems. This was an attempt to resolve thedilemmaofhowto dealwiththeneedfornarrow-focusspecializedworkshops yet accommodate the presentation of new theories and techniques that blur the distinction between the statistical and the structural approaches. A total of 219 papers were received from many countries, with the subm- sion and reviewing processes being carried out separately for each workshop. A total of 59 papers were accepted for oral presentation and 64 for posters. In - dition, four invited speakers presented informative talks and overviews of their research. They were: Alberto Sanfeliu, from the Technical University of Cata- nia, Spain; Marco Gori, from the University of Siena, Italy; Nello Cristianini, from the University of California, USA; and Erkki Oja, from Helsinki University of Technology, Finland, winner of the 2004 Pierre Devijver Award.

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.

Biometric authentication is increasingly gaining popularity in a large spectrum ofapplications,rangingfromgovernmentprograms(e. g. ,nationalIDcards,visas for international travel,and the ?ght against terrorism) to personal applications such as logical and physical access control. Although a number of e?ective - lutions are currently available, new approaches and techniques are necessary to overcomesomeofthelimitationsofcurrentsystemsandtoopenupnewfrontiers in biometric research and development. The 30 papers presented at Biometric Authentication Workshop 2004 (BioAW 2004) provided a snapshot of current research in biometrics, and identify some new trends. This volume is composed of?vesections:facerecognition,?ngerprintrecognition,templateprotectionand security, other biometrics, and fusion and multimodal biometrics. For classical biometrics like ?ngerprint and face recognition, most of the papers in Sect. 1 and 2 address robustness issues in order to make the biometric systems work in suboptimal conditions: examples include face detection and recognition - der uncontrolled lighting and pose variations, and ?ngerprint matching in the case of severe skin distortion. Benchmarking and interoperability of sensors and liveness detection are also topics of primary interest for ?ngerprint-based s- tems. Biometrics alone is not the solution for complex security problems. Some of the papers in Sect. 3 focus on designing secure systems; this requires dealing with safe template storage, checking data integrity, and implementing solutions in a privacy-preserving fashion. The match-on-tokens approach, provided that current accuracy and cost limitations can be satisfactorily solved by using new algorithms and hardware, is certainly a promising alternative. The use of new biometric indicators like eye movement, 3D ?nger shape, and soft traits (e. g.

The past decade has seen a rapid growth in the demand for biometric-based - thentication solutions for a number of applications. With signi?cant advances in biometrictechnologyandanincreaseinthenumberofapplicationsincorporating biometrics, it is essential that we bring together researchers from academia and industry as well as practitioners to share ideas, problems and solutions for the development and successful deployment of state-of-the-art biometric systems. The InternationalConference onBiometric Authentication (ICBA 2004)was the ?rst major gathering in the Asia-Paci?c region devoted to facilitating this interaction. We are pleased that this conference attracted a large number of high-quality research papers that will bene't the international biometrics - search community. After a careful review of 157 submissions, 101 papers were acceptedeitherasoral(35)orposter(66)presentations.Inadditiontothesete- nical presentations, this conference also presented the results and summaries of threebiometric competitions: FingerprintVeri?cationCompetition (FVC 2004), Face Authentication Competition (FAC 2004), and Signature Veri?cation C- petition (SVC 2004). This conference provided a forum for the practitioners to discuss their practical experiences in applying the state-of-the-art biometric technologies which will further stimulate research in biometrics. We aregrateful to Jim L. Wayman, Edwin Rood, Raymond Wong, Jonathon Philips, andFrancisHoforacceptingourinvitationtogivekeynotetalksatICBA 2004. In addition, we would like to express our gratitude to all the contributors, reviewers, program committee and organizing committee members who made this a very successful conference. We also wish to acknowledge the Croucher Foundation, the International Association of Pattern Recognition, IEEE Hong Kong Section, the Hong Kong Polytechnic University, the National Natural S- ence Foundation in China, and Springer-Verlag for sponsoring this conference

The 15th Annual Symposium on Combinatorial Pattern Matching was held in Ciragan Palace Hotel, Istanbul, Turkey during July 5 7, 2004. CPM 2004 - peated the success of its predecessors; it even surpassed them in terms of the numberofinvitedspeakers, thenumberofsubmissions, andthenumberofpapers accepted and presented at the conference. In response to the call for papers, CPM 2004 received a record number of 79 high-quality submissions. Each submission was reviewed by at least three program committee members and the comments were returned to the authors. Following an extensive electronic discussion period, the Program Committee accepted36ofthesubmissionstobepresentedattheconference.Theyconstitute originalresearchcontributionsincombinatorialpatternmatchingalgorithmsand datastructures, molecularsequenceanalysis, phylogenetictreeconstruction, and RNA and protein structure analysis and prediction. CPM 2004 had ?ve invited speakers. In alphabetical order they were: Evan Eichler from the University of Washington, USA, Martin Farach-Colton from Rutgers University, USA, Paolo Ferragina from the University of Pisa, Italy, Piotr Indyk from MIT, USA, and Gene Myers from the University of California, Berkeley, USA. It is impossible to organize such a successful program without the help of many individuals. We would like to express our appreciation to the authors of the submitted papers and to the program committee members and external referees, who provided timely and signi?cant reviews. July 2004 S.C. Sahinalp, S. Muthukrishnan, U. Dogrusoz Organization CPM 2004 was locally organized by Bilkent University, Ankara, Turkey. Within Bilkent University, the Center for Bioinformatics (BCBI) and the Computer Engineering Department cooperate

This volume provides students, researchers and application developers with the knowledge and tools to get the most out of using neural networks and related data modelling techniques to solve pattern recognition problems. Each chapter covers a group of related pattern recognition techniques and includes a range of examples to show how these techniques can be applied to solve practical problems. Features of particular interest include:- A NETLAB toolbox which is freely available via the Internet at http://www.ncrg.aston.ac.uk/netlab- Worked examples, demonstration programs and over 100 graded exercises- Cutting edge research made accessible for the first time in a highly usable form- Comprehensive coverage of visualisation methods, Bayesian techniques for neural networks and Gaussian ProcessesAlthough primarily a textbook for teaching undergraduate and postgraduate courses in pattern recognition and neural networks, this book will also be of interest to practitioners and researchers who can use the toolbox to develop application solutions and new models."...provides a unique collection of many of the most important pattern recognition algorithms. With its use of compact and easily modified MATLAB scripts, the book is ideally suited to both teaching and research."Christopher Bishop, Microsoft Research, Cambridge, UK"...a welcome addition to the literature on neural networks and how to train and use them to solve many of the statistical problems that occur in data analysis and data mining" Jack Cowan, Mathematics Department, University of Chicago, US"If you have a pattern recognition problem, you should consider NETLAB; if you use NETLAB you must have this book." Keith Worden, University of Sheffield, UK

The Distinguished Dissertation Series is published on behalf of the Conference of Professors and Heads of Computing and the British Computer Society, who annually select the best British PhD dissertations in computer science for publication. The dissertations are selected on behalf of the CPHC by a panel of eight academics. Each dissertation chosen makes a noteworthy contribution to the subject and reaches a high standard of exposition, placing all results clearly in the context of computer science as a whole. In this way computer scientists with significantly different interests are able to grasp the essentials - or even find a means of entry - to an unfamiliar research topic. This book investigates how information contained in multiple, overlapping images of a scene may be combined to produce images of superior quality. This offers possibilities such as noise reduction, extended field of view, blur removal, increased spatial resolution and improved dynamic range. Potential applications cover fields as diverse as forensic video restoration, remote sensing, video compression and digital video editing. The book covers two aspects that have attracted particular attention in recent years: image mosaicing, whereby multiple images are aligned to produce a large composite; and super-resolution, which permits restoration at an increased resolution of poor quality video sequences by modelling and removing imaging degradations including noise, blur and spacial-sampling. It contains a comprehensive coverage and analysis of existing techniques, and describes in detail novel, powerful and automatic algorithms (based on a robust, statistical framework) for applying mosaicing and super-resolution. The algorithms may be implemented directly from the descriptions given here. A particular feature of the techniques is that it is not necessary to know the camera parameters (such as position and focal length) in order to apply them. Throughout the book, examples are given on real image sequences, covering a variety of applications including: the separation of latent marks in forensic images; the automatic creation of 360 panoramic mosaics; and super-resolution restoration of various scenes, text, and faces in lw-quality video.