This two volume set LNCS 6791 and LNCS 6792 constitutes the refereed proceedings of the 21th International Conference on Artificial Neural Networks, ICANN 2011, held in Espoo, Finland, in June 2011.
The 106 revised full or poster papers presented were carefully reviewed and selected from numerous submissions. ICANN 2011 had two basic tracks: brain-inspired computing and machine learning research, with strong cross-disciplinary interactions and applications.

st The world of the 21 century is, more than ever, global and impersonal. Criminal and terrorist threats, both physical and on the Internet, increase by the day. The demand for better methods of identification and access control is growing, not only in companies and organisations but also in the world at large. At the same time, such security measures have to be balanced with means for protecting the privacy of users. Identity management is put under pressure, due to the growing number of frauds who want to hide their true identity. This challenges the information security research community to focus on interdisciplinary and holistic approaches while retaining the benefits of previous research efforts. In this context, the IFIP Working Group 11.6 on Identity Management has been founded in August 2006. The intention of the Working Group is to offer a broad forum for the exchange of knowledge and for the tracking and discussion of issues and new developments. In this, we take an interdisciplinary approach. Scientists as well as practitioners, from government and business, who are involved in the field of identity management are welcome to participate. The IDMAN 2007 Conference on Policies and Research in Identity Management was the very first conference organized by this Working Group. We aim to organize conferences bi-annually. The IDMAN 2007 Conference has been centered around the theme of National Identity Management or, in other words, identity management in the public sector.

This book collects the lectures given at the NATO Advanced Study Institute From Identijication to Learning held in Villa Olmo, Como, Italy, from August 22 to September 2, 1994. The school was devoted to the themes of Identijication, Adaptation and Learning, as they are currently understood in the Information and Contral engineering community, their development in the last few decades, their inter connections and their applications. These titles describe challenging, exciting and rapidly growing research areas which are of interest both to contral and communication engineers and to statisticians and computer scientists. In accordance with the general goals of the Institute, and notwithstanding the rat her advanced level of the topics discussed, the presentations have been generally kept at a fairly tutorial level. For this reason this book should be valuable to a variety of rearchers and to graduate students interested in the general area of Control, Signals and Information Pracessing. As the goal of the school was to explore a common methodologicalline of reading the issues, the flavor is quite interdisciplinary. We regard this as an original and valuable feature of this book."

The recent development of intelligent surveillance systems has captured the interest of both academic research labs and industry. Automated Multi-Camera Surveillance addresses monitoring of people and vehicles, and detection of threatening objects and events in a variety of scenarios. In this book, techniques for development of an automated multi-camera surveillance system are discussed and proposed. The state-of-the-art in the automated surveillance systems is reviewed as well. Detailed explanation of sub-components of surveillance systems are provided, and enhancements to each of these components are proposed. The authors identify important challenges that such a system must address, and propose solutions. Development of a specific surveillance system called "KNIGHT" is described, along with the authors' experience using it. This book enables the reader to understand the mathematical models and algorithms underlying automated surveillance as well as the benefits and limitations of using such methods.

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

Over the last few decades, research on handwriting recognition has made impressive progress. The research and development on handwritten word recognition are to a large degree motivated by many application areas, such as automated postal address and code reading, data acquisition in banks, text-voice conversion, security, etc. As the prices of scanners, com puters and handwriting-input devices are falling steadily, we have seen an increased demand for handwriting recognition systems and software pack ages. Some commercial handwriting recognition systems are now available in the market. Current commercial systems have an impressive performance in recognizing machine-printed characters and neatly written texts. For in stance, High-Tech Solutions in Israel has developed several products for container ID recognition, car license plate recognition and package label recognition. Xerox in the U. S. has developed TextBridge for converting hardcopy documents into electronic document files. In spite of the impressive progress, there is still a significant perfor mance gap between the human and the machine in recognizing off-line unconstrained handwritten characters and words. The difficulties encoun tered in recognizing unconstrained handwritings are mainly caused by huge variations in writing styles and the overlapping and the interconnection of neighboring characters. Furthermore, many applications demand very high recognition accuracy and reliability. For example, in the banking sector, although automated teller machines (ATMs) and networked banking sys tems are now widely available, many transactions are still carried out in the form of cheques."

This book constitutes the refereed proceedings of the 9th International Conference on Smart Homes and Health Telematics, ICOST 2011, held in Montreal, Canada, in June 2011. The 25 revised full papers presented together with 16 short papers and 8 student papers were carefully reviewed and selected from 94 submissions. The papers are organized in topical sections on smart home and village; health telematics and healthcare technology; wellbeing, ageing friendly and enabling technology; and medical health telematics and healthcare technology.

Integrates computer vision, pattern recognition, and AI.

Presents original research that will benefit researchers and professionals in computer vision, pattern recognition, target recognition, machine learning, evolutionary learning, image processing, knowledge discovery and data mining, cybernetics, robotics, automation and psychology

From the reviews: "This book is very well written and contains many important and new original results that certainly play an important role in today 's nonlinear optics." Physicalia

This two-volume set LNCS 6691 and 6692 constitutes the refereed proceedings of the 11th International Work-Conference on Artificial Neural Networks, IWANN 2011, held in Torremolinos-M laga, Spain, in June 2011. The 154 revised papers were carefully reviewed and selected from 202 submissions for presentation in two volumes. The second volume includes 76 papers organized in topical sections on video and image processing; hybrid artificial neural networks: models, algorithms and data; advances in machine learning for bioinformatics and computational biomedicine; biometric systems for human-machine interaction; data mining in biomedicine; bio-inspired combinatorial optimization; applying evolutionary computation and nature-inspired algorithms to formal methods; recent advances on fuzzy logic and soft computing applications; new advances in theory and applications of ICA-based algorithms; biological and bio-inspired dynamical systems; and interactive and cognitive environments. The last section contains 9 papers from the International Workshop on Intelligent Systems for Context-Based Information Fusion, ISCIF 2011, held at IWANN 2011.

We welcome you to the First International Conference on Arts and Technology (ArtsIT 2009), hosted by CSIE of the National Ilan University and co-organized by the National Science Council, ICST, College of EECS at National Ilan University, Software Simulation Society in Taiwan, ISAC, TCA, NCHC, CREATE-NET, and Institute for Information Industry. ArtsIT2009 was held in Yilan, Taiwan, during September 24-25, 2009. The conference comprised the following themes: * New Media Technologies (Evolutionary systems that create arts or display art works, such as tracking sensors, wearable computers, mixed reality, etc. ) * Software Art (Image processing or computer graphics techniques that create arts, including algorithmic art, mathematic art, advanced modeling and rend- ing, etc. ) * Animation Techniques (2D or 3D computer animations, AI-based animations, etc. ) * Multimedia (Integration of different media, such as virtual reality systems, audio, performing arts, etc. ) * Interactive Methods (Vision-based tracking and recognition, interactive art, etc. ) The conference program started with an opening ceremony, followed by three keynote speeches and four technical sessions distributed over a period of two days. Two poster sessions, one hour each, were scheduled before the afternoon oral sessions. An Int- active Arts Exhibition was held in conjunction with ArtsIT 2009. Twelve well-known digital arts teams from Taiwan exhibited 15 artworks in this event, including 10 int- active installation arts, 4 video arts, and 1 digital print. The conference received around 50 submissions from 15 different countries.

This comprehensive textbook on data mining details the unique steps of the knowledge discovery process that prescribes the sequence in which data mining projects should be performed, from problem and data understanding through data preprocessing to deployment of the results. This knowledge discovery approach is what distinguishes Data Mining from other texts in this area.

The book provides a suite of exercises and includes links to instructional presentations. Furthermore, it contains appendices of relevant mathematical material.

Clustering is one of the most fundamental and essential data analysis techniques. Clustering can be used as an independent data mining task to discern intrinsic characteristics of data, or as a preprocessing step with the clustering results then used for classification, correlation analysis, or anomaly detection.

Kogan and his co-editors have put together recent advances in clustering large and high-dimension data. Their volume addresses new topics and methods which are central to modern data analysis, with particular emphasis on linear algebra tools, opimization methods and statistical techniques. The contributions, written by leading researchers from both academia and industry, cover theoretical basics as well as application and evaluation of algorithms, and thus provide an excellent state-of-the-art overview.

The level of detail, the breadth of coverage, and the comprehensive bibliography make this book a perfect fit for researchers and graduate students in data mining and in many other important related application areas.

The three-volume set LNCS 6675, 6676 and 6677 constitutes the refereed proceedings of the 8th International Symposium on Neural Networks, ISNN 2011, held in Guilin, China, in May/June 2011. The total of 215 papers presented in all three volumes were carefully reviewed and selected from 651 submissions. The contributions are structured in topical sections on computational neuroscience and cognitive science; neurodynamics and complex systems; stability and convergence analysis; neural network models; supervised learning and unsupervised learning; kernel methods and support vector machines; mixture models and clustering; visual perception and pattern recognition; motion, tracking and object recognition; natural scene analysis and speech recognition; neuromorphic hardware, fuzzy neural networks and robotics; multi-agent systems and adaptive dynamic programming; reinforcement learning and decision making; action and motor control; adaptive and hybrid intelligent systems; neuroinformatics and bioinformatics; information retrieval; data mining and knowledge discovery; and natural language processing.

Many computer scientists, engineers, applied mathematicians, and physicists use geometry theory and geometric computing methods in the design of perception-action systems, intelligent autonomous systems, and man-machine interfaces. This handbook brings together the most recent advances in the application of geometric computing for building such systems, with contributions from leading experts in the important fields of neuroscience, neural networks, image processing, pattern recognition, computer vision, uncertainty in geometric computations, conformal computational geometry, computer graphics and visualization, medical imagery, geometry and robotics, and reaching and motion planning. For the first time, the various methods are presented in a comprehensive, unified manner.

This handbook is highly recommended for postgraduate students and researchers working on applications such as automated learning; geometric and fuzzy reasoning; human-like artificial vision; tele-operation; space maneuvering; haptics; rescue robots; man-machine interfaces; tele-immersion; computer- and robotics-aided neurosurgery or orthopedics; the assembly and design of humanoids; and systems for metalevel reasoning.

Markov random field (MRF) theory provides a basis for modeling contextual constraints in visual processing and interpretation. It enables us to develop optimal vision algorithms systematically when used with optimization principles. This book presents a comprehensive study on the use of MRFs for solving computer vision problems. Various vision models are presented in a unified framework, including image restoration and reconstruction, edge and region segmentation, texture, stereo and motion, object matching and recognition, and pose estimation. This third edition includes the most recent advances and has new and expanded sections on topics such as: Bayesian Network; Discriminative Random Fields; Strong Random Fields; Spatial-Temporal Models; Learning MRF for Classification. This book is an excellent reference for researchers working in computer vision, image processing, statistical pattern recognition and applications of MRFs. It is also suitable as a text for advanced courses in these areas.

This book contains an edited collection of eighteen contributions on soft and hard computing techniques and their applications to autonomous robotic systems. Each contribution has been exclusively written for this volume by a leading researcher. The volume demonstrates the various ways that the soft computing and hard computing techniques can be used in different integrated manners to better develop autonomous robotic systems that can perform various tasks of vision, perception, cognition, thinking, pattern recognition, decision-making, and reasoning and control, amongst others. Each chapter of the book is self-contained and points out the future direction of research.

"It is a must reading for students and researchers interested in exploring the potentials of the fascinating field that will form the basis for the design of the intelligent machines of the future"
(Madan M. Gupta)

This volume contains the proceedings of the third international conference on Pattern Recognition and Machine Intelligence (PReMI 2009) which was held at the Indian Institute of Technology, New Delhi, India, during December 16-20, 2009. This was the third conference in the series. The first two conferences were held in December at the Indian Statistical Institute, Kolkata in 2005 and 2007. PReMI has become a premier conference in India presenting state-of-art research findings in the areas of machine intelligence and pattern recognition. The conference is also successful in encouraging academic and industrial interaction, and in prom- ing collaborative research and developmental activities in pattern recognition, - chine intelligence and other allied fields, involving scientists, engineers, professionals, researchers and students from India and abroad. The conference is scheduled to be held every alternate year making it an ideal platform for sharing views and expe- ences in these fields in a regular manner. The focus of PReMI 2009 was soft-computing, machine learning, pattern recognition and their applications to diverse fields. As part of PReMI 2009 we had two special workshops. One workshop focused on text mining. The other workshop show-cased industrial and developmental projects in the relevant areas. Premi 2009 attracted 221 submissions from different countries across the world.

th This two-volume set constitutes the Proceedings of the 16 International Conference on Neural Information Processing (ICONIP 2009), held in Bangkok, Thailand, during December 1-5, 2009. ICONIP is a world-renowned international conference that is held annually in the Asia-Pacific region. This prestigious event is sponsored by the Asia Pacific Neural Network Assembly (APNNA), and it has provided an annual forum for international researchers to exchange the latest ideas and advances in neural networks and related discipline. The School of Information Technology (SIT) at King Mongkut's University of Technology Thonburi (KMUTT), Bangkok, Thailand was the proud host of ICONIP 2009. The conference theme was "Challenges and Trends of Neural Information Processing," with an aim to discuss the past, present, and future challenges and trends in the field of neural information processing. ICONIP 2009 accepted 145 regular session papers and 53 special session papers from a total of 466 submissions received on the Springer Online Conference Service (OCS) system. The authors of accepted papers alone covered 36 countries and - gions worldwide and there are over 500 authors in these proceedings. The technical sessions were divided into 23 topical categories, including 9 special sessions.

Following two successful events in Guilin, People's Republic of China (KSEM 2006) and in Melbourne, Australia (KSEM 2007) the third event in this conference series was held for the first time in Europe, namely, in Vienna, Austria. KSEM 2009 aimed to be a communication platform and meeting ground for research on knowledge science, engineering and management, attracting high-quality, state-of-the-art publications from all over the world. It offers an exceptional opportunity for presenting original work, technological advances, practical problems and concerns of the research community. The importance of studying "knowledge" from different viewpoints such as science, engineering and management has been widely acknowledged. The accelerating pace of the "Internet age" challenges organizations to compress communication and innovation cycles to achieve a faster return on investment for knowledge. Thus, next-generation business solutions must be focused on supporting the creation of value by adding knowledge-rich components as an integral part to the work process. Therefore, an integrated approach is needed, which combines issues from a large array of knowledge fields such as science, engineering and management. Based on the reviews by the members of the Program Committee and the additional reviewers, 42 papers were selected for this year's conference. Additionally, two discussion panels dealing with "Knowware: The Third Star after Hardware and Software" and "Required Knowledge for Delivering Services" took place under the auspices of the conference. The papers and the discussions covered a great variety of approaches of knowledge science, management and engineering, thus making KSEM a unique conference.

The Radial Basis Function (RBF) network has gained in popularity in recent years. This is due to its desirable properties in classification and functional approximation applications, accompanied by training that is more rapid than that of many other neural-network techniques. RBF network research has focused on enhanced training algorithms and variations on the basic architecture to improve the performance of the network. In addition, the RBF network is proving to be a valuable tool in a diverse range of applications areas, for example, robotics, biomedical engineering, and the financial sector. The two-title series Theory and Applications of Radial Basis Function Networks provides a comprehensive survey of recent RBF network research. This volume, New Advances in Design, contains a wide range of applications in the laboratory and case-studies describing current use. The sister volume to this one, Recent Developments in Theory and Applications, covers advances in training algorithms, variations on the architecture and function of the basis neurons, and hybrid paradigms. The combination of the two volumes will prove extremely useful to practitioners in the field, engineers, researchers, students and technically accomplished managers.

The 14th Iberoamerican Congress on Pattern Recognition (CIARP 2009, C- gresoIberoAmericanodeReconocimientodePatrones)formedthelatestofanow longseriesofsuccessfulmeetingsarrangedbytherapidlygrowingIberoamerican pattern recognition community. The conference was held in Guadalajara, Jalisco, Mexico and organized by the Mexican Association for Computer Vision, Neural Computing and Robotics (MACVNR). It was sponsodred by MACVNR and ?ve other Iberoamerican PR societies. CIARP 2009 was like the previous conferences in the series supported by the International Association for Pattern Recognition (IAPR). CIARP 2009 attracted participants from all over the world presenting sta- of-the-artresearchon mathematical methods and computing techniques for p- tern recognition, computer vision, image and signal analysis, robot vision, and speech recognition, as well as on a wide range of their applications. This time the conference attracted participants from 23 countries,9 in Ibe- america, and 14 from other parts of the world. The total number of submitted papers was 187, and after a serious review process 108 papers were accepted, all of them with a scienti?c quality above overall mean rating. Sixty-four were selected as oral presentations and 44 as posters. Since 2008 the conference is almost single track, and therefore there was no real grading in quality between oral and poster papers. As an acknowledgment that CIARP has established itself as a high-quality conference, its proceedings appear in the Lecture Notes in Computer Science series. Moreover, its visibility is further enhanced by a selection of a set of papers that will be published in a special issue of the journal Pattern Recognition Letters.

The concept of CAST as Computer Aided Systems Theory was introduced by F. Pichler in the late 1980s to refer to computer theoretical and practical developments as tools for solving problems in system science. It was thought of as the third component (the other two being CAD and CAM) required to complete the path from computer and systems sciences to practical developments in science and engineering. Franz Pichler, of the University of Linz, organized the first CAST workshop in April 1988, which demonstrated the acceptance of the concepts by the scientific and technical community. Next, the University of Las Palmas de Gran Canaria joined the University of Linz to organize the first international meeting on CAST (Las Palmas, February 1989) under the name EUROCAST'89. This proved to be a very successful gathering of systems theorists, computer scientists and engineers from most European countries, North America and Japan. It was agreed that EUROCAST international conferences would be organized every two years, alternating between Las Palmas de Gran Canaria and a continental European location. From 2001 the conference has been held exclusively in Las Palmas. Thus, successive EUROCAST meetings took place in Krems (1991), Las Palmas (1993), In- bruck (1995), Las Palmas (1997), Vienna (1999), Las Palmas (2001), Las Palmas (2003) Las Palmas (2005) and Las Palmas (2007), in addition to an extra-European CAST c- ference in Ottawa in 1994.

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.