This volume contains the Proceedings of the 9th Italian Workshop on Neural Nets WIRN VIETRI-97, organised by the International Institute for Advanced Scientific Studies ((Eduardo R. Caianiello" (IIASS), the Societa Italiana Reti Neuroniche (SIREN) and the IEEE NNC Italian RIG. As in the previous editions some invited and reviewed talks on updated subjects are presented in addition to the original contributions selected by the Refereeing Committee. Also included is Professor C.M. Bishop's Invited paper on: * Latent Variables, Topographic Mappings and Data Visualization; and two review talks that deal with updated topics: * Fuzzy Neural Networks for Pattern Recognition; * A Unifying View of Gradient Calculations and Learning for Locally Recurrent Neural Networks; For publication the original contributions have been assembled into 4 sections: Applications, Architectures and Algorithms, Mathematical Models, Pattern Recognition and Robotics. The Editors thank the invited speaker and all the participants for having contributed to the success of the Workshop by submitting high quality manuscripts, and also express gratitude to the Refereeing Committee for the high quality of the selection process. Maria Marinaro Roberto Tagliaferri VI Organizing -Scientific Committee: B. Apolloni (Univ. Milano), A. Bertoni (Univ. Milano), D.O. Caviglia (Univ. Genova), P. Campadelli (Univ. Milano), A. Colla (ELSAG BAILEY -Genova), M. Frixione (1IASS), C. Furlanello (IRST -Trento), A. Esposito (1IASS), G.M. Guazzo (1IASS), M. Gori (Univ. Firenze), F. Lauria (Univ. Napoli), M. Marinaro (Univ. Salerno - IIASS), F.

This book constitutes the refereed proceedings of the Chinese Conference on Image and Graphics Technologies and Applications, IGTA 2013, held in Beijing, China, in April 2013. The 40 papers and posters presented were carefully reviewed and selected from 89 submissions. The papers address issues such as the generation of new ideas, new approaches, new techniques, new applications and new evaluation in the field of image processing and graphics.

ICMCCA 2012 is the first International Conference on Multimedia Processing, Communication and Computing Applications and the theme of the Conference is chosen as 'Multimedia Processing and its Applications'. Multimedia processing has been an active research area contributing in many frontiers of today's science and technology. This book presents peer-reviewed quality papers on multimedia processing, which covers a very broad area of science and technology. The prime objective of the book is to familiarize readers with the latest scientific developments that are taking place in various fields of multimedia processing and is widely used in many disciplines such as Medical Diagnosis, Digital Forensic, Object Recognition, Image and Video Analysis, Robotics, Military, Automotive Industries, Surveillance and Security, Quality Inspection, etc. The book will assist the research community to get the insight of the overlapping works which are being carried out across the globe at many medical hospitals and institutions, defense labs, forensic labs, academic institutions, IT companies and security & surveillance domains. It also discusses latest state-of-the-art research problems and techniques and helps to encourage, motivate and introduce the budding researchers to a larger domain of multimedia.

This book constitutes the refereed proceedings of CVM 2012, the First International Conference on Computational Visual Media, held in Beijing, China, in November 2012.
The 33 revised full papers were carefully reviewed and selected from 81 submissions. The papers are organized in topical sections on image processing I and II, geometric processing, saliency, recognition, perception and learning, shape analysis, media retrieval, and capture, rendering and visualization.

This book contains the manuscripts of the papers delivered at the International Sym posium on Synergetics held at SchloB Elmau, Bavaria, Germany, from April 30 until May 5, 1979. This conference followed several previous ones (Elmau 1972, Sicily 1974, Elmau 1977). This time the subject of the symposium was "pattern formation by dynam ic systems and pattern recognition." The meeting brought together scientists from such diverse fields as mathematics, physics, chemistry, biology, history as well as experts in the fields of pattern recognition and associative memory. When I started this type of conference in 1972 it appeared to be a daring enter prise. Indeed, we began to explore virgin land of science: the systematic study of cooperative effects in physical systems far from equi ibrium and in other disciplines. Though these meetings were attended by scientists from quite different disciplines, a basic concept and even a common language were found from the very beginning. The idea that there exist profound analogies in the behaviour of large classes of complex systems, though the systems themselves may be quite different, proved to be most fruitful. I was delighted to see that over the past one or two years quite similar conferences were now held in various places allover the world. The inclusion of prob lems of pattern recognition at the present meeting is a novel feature, however."

As is true with most areas of Artificial Intelligence, there is real need for a symbiotic relationship between the biological and artificial - a need for problems to be viewed from many different angles, and particularly so in the study of vision. The INSIGHT consortium is taking steps in this direction. In a traditional sense, the papers in this volume are represented by the areas of neuroscience, psychophysics and traditional computer vision. However, to gain deeper insight into vision processes, it is the interaction of scientific ideas from these areas that is essential. The scope of the topics discussed has a definite interdisciplinary flavour: at one end of the spectrum we have experiments performed and direct measurement of the responses of neurons to visual stimuli; at the other end we have the mathematical and computational aspects of optical flow (the relative motion between observer and object) and approaches of tackling vision through binocular disparities (stereopsis). Traditional edge detection (essential for the initial classification of shape) is also covered as is the study of natural texture patterns that occur on object surfaces. A fundamental aim of the Basic Research part of the ESPRIT programme is the pro duction and maintenance of a pool of research expertise in Europe, from which both fur ther research and industry can draw. As the authors state in their preface, this project has not only succesfully merged the talents of senior researchers from different backgrounds, but also brought many young ones along."

Surface properties play a very important role in many perception tasks. Object recognition, navigation, and inspection use surface properties ex tensively. Characterizing surfaces at different scales in given data is often the first and possibly the most important step. Most early research in ma chine perception relied on only very coarse characterization of surfaces. In the last few years, surface characterization has been receiving due attention. Dr. T. J. Fan is one of the very few researchers who designed and im plemented a complete system for object recognition. He studied issues re lated to characterization of surfaces in the context of object recognition, and then uses the features thus developed for recognizing objects. He uses a multi-view representation of 3-D objects for recognition, and he devel ops techniques for the segmentation of range images to obtain features for recognition. His matching approach also allows him to recognize objects from their partial views in the presence of other occluding objects. The efficacy of his approach is demonstrated in many examples."

Pattern recognition is a child of modern technology; electronics and computers in particular have inspired research and made it possible to develop the subject in a way which would have been impossible otherwise. It is a rapidly growing research field which began to flourish in the 1960s and which is beginning to produce commercial devices. Significant developments have been made, both in the theory and practical engineering of the subject, but there is evidence of a schism developing between these two approaches. Practical machines have usually been designed on an ad hoc basis, with little use being made of advanced theory. It is difficult to provide a rigorous mathematical treatment of many problems pertinent to a practical situation. This is due, in part at least, to a conceptual rift between theory and practice. The mathematics of optimal systems is well developed, whereas pragmatists are more concerned with vaguer ideas of reasonable and sufficient. In some situations, the quest for optimality can constrain research and retard practical progress. This can occur, for example, if too narrow a view is taken of "optimal": the accuracy of a system may be optimal whereas its speed, cost, or physical size may be grossly suboptimal. The objective of this book is to present a glimpse of the pragmatic approach to pattern recognition; there already exist a number of excellent texts describing theoretical developments.

Document image analysis is the automatic computer interpretation of images of printed and handwritten documents, including text, drawings, maps, music scores, etc. Research in this field supports a rapidly growing international industry. This is the first book to offer a broad selection of state-of-the-art research papers, including authoritative critical surveys of the literature, and parallel studies of the architectureof complete high-performance printed-document reading systems. A unique feature is the extended section on music notation, an ideal vehicle for international sharing of basic research. Also, the collection includes important new work on line drawings, handwriting, character and symbol recognition, and basic methodological issues. The IAPR 1990 Workshop on Syntactic and Structural Pattern Recognition is summarized, including the reports of its expert working groups, whose debates provide a fascinating perspective on the field. The book is an excellent text for a first-year graduate seminar in document image analysis, and is likely to remain a standard reference in the field for years.

Keith M. Ponting Speech Research Unit, DERA Malvern St. Andrew's Road, Great Malvern, Worcs. WR14 3PS, UK email: ponting

The visualization of human anatomy for diagnostic, therapeutic, and educational pur poses has long been a challenge for scientists and artists. In vivo medical imaging could not be introduced until the discovery of X-rays by Wilhelm Conrad ROntgen in 1895. With the early medical imaging techniques which are still in use today, the three-dimensional reality of the human body can only be visualized in two-dimensional projections or cross-sections. Recently, biomedical engineering and computer science have begun to offer the potential of producing natural three-dimensional views of the human anatomy of living subjects. For a broad application of such technology, many scientific and engineering problems still have to be solved. In order to stimulate progress, the NATO Advanced Research Workshop in Travemiinde, West Germany, from June 25 to 29 was organized. It brought together approximately 50 experts in 3D-medical imaging from allover the world. Among the list of topics image acquisition was addressed first, since its quality decisively influences the quality of the 3D-images. For 3D-image generation - in distinction to 2D imaging - a decision has to be made as to which objects contained in the data set are to be visualized. Therefore special emphasis was laid on methods of object definition. For the final visualization of the segmented objects a large variety of visualization algorithms have been proposed in the past. The meeting assessed these techniques.

Medical imaging is an important topic and plays a key role in robust diagnosis and patient care. It has experienced an explosive growth over the last few years due to imaging modalities such as X-rays, computed tomography (CT), magnetic resonance (MR) imaging, and ultrasound. This book focuses primarily on model-based segmentation techniques, which are applied to cardiac, brain, breast and microscopic cancer cell imaging. It includes contributions from authors working in industry and academia, and presents new material.

The three volume set LNCS 7062, LNCS 7063, and LNCS 7064 constitutes the proceedings of the 18th International Conference on Neural Information Processing, ICONIP 2011, held in Shanghai, China, in November 2011. The 262 regular session papers presented were carefully reviewed and selected from numerous submissions. The papers of part I are organized in topical sections on perception, emotion and development, bioinformatics, biologically inspired vision and recognition, bio-medical data analysis, brain signal processing, brain-computer interfaces, brain-like systems, brain-realistic models for learning, memory and embodied cognition, Clifford algebraic neural networks, combining multiple learners, computational advances in bioinformatics, and computational-intelligent human computer interaction. The second volume is structured in topical sections on cybersecurity and data mining workshop, data mining and knowledge doscovery, evolutionary design and optimisation, graphical models, human-originated data analysis and implementation, information retrieval, integrating multiple nature-inspired approaches, kernel methods and support vector machines, and learning and memory. The third volume contains all the contributions connected with multi-agent systems, natural language processing and intelligent Web information processing, neural encoding and decoding, neural network models, neuromorphic hardware and implementations, object recognition, visual perception modelling, and advances in computational intelligence methods based pattern recognition.

The three volume set LNCS 7062, LNCS 7063, and LNCS 7064 constitutes the proceedings of the 18th International Conference on Neural Information Processing, ICONIP 2011, held in Shanghai, China, in November 2011.
The 262 regular session papers presented were carefully reviewed and selected from numerous submissions.
The papers of part I are organized in topical sections on perception, emotion and development, bioinformatics, biologically inspired vision and recognition, bio-medical data analysis, brain signal processing, brain-computer interfaces, brain-like systems, brain-realistic models for learning, memory and embodied cognition, Clifford algebraic neural networks, combining multiple learners, computational advances in bioinformatics, and computational-intelligent human computer interaction.
The second volume is structured in topical sections on cybersecurity and data mining workshop, data mining and knowledge doscovery, evolutionary design and optimisation, graphical models, human-originated data analysis and implementation, information retrieval, integrating multiple nature-inspired approaches, Kernel methods and support vector machines, and learning and memory.
The third volume contains all the contributions connected with multi-agent systems, natural language processing and intelligent Web information processing, neural encoding and decoding, neural network models, neuromorphic hardware and implementations, object recognition, visual perception modelling, and advances in computational intelligence methods based pattern recognition.

This volume proceedings contains revised selected papers from the 4th International Conference on Artificial Intelligence and Computational Intelligence, AICI 2012, held in Chengdu, China, in October 2012. The total of 163 high-quality papers presented were carefully reviewed and selected from 724 submissions. The papers are organized into topical sections on applications of artificial intelligence, applications of computational intelligence, data mining and knowledge discovery, evolution strategy, expert and decision support systems, fuzzy computation, information security, intelligent control, intelligent image processing, intelligent information fusion, intelligent signal processing, machine learning, neural computation, neural networks, particle swarm optimization, and pattern recognition.

A guide on the use of SVMs in pattern classification, including a rigorous performance comparison of classifiers and regressors. The book presents architectures for multiclass classification and function approximation problems, as well as evaluation criteria for classifiers and regressors. Features: Clarifies the characteristics of two-class SVMs; Discusses kernel methods for improving the generalization ability of neural networks and fuzzy systems; Contains ample illustrations and examples; Includes performance evaluation using publicly available data sets; Examines Mahalanobis kernels, empirical feature space, and the effect of model selection by cross-validation; Covers sparse SVMs, learning using privileged information, semi-supervised learning, multiple classifier systems, and multiple kernel learning; Explores incremental training based batch training and active-set training methods, and decomposition techniques for linear programming SVMs; Discusses variable selection for support vector regressors.

This book constitutes the refereed proceedings of the Second International Workshop on Multimodal Brain Image Analysis, held in conjunction with MICCAI 2012, in Nice, France, in October 2012. The 19 revised full papers presented were carefully reviewed and selected from numerous submissions. The objective of this workshop is to forward the state of the art in analysis methodologies, algorithms, software systems, validation approaches, benchmark datasets, neuroscience, and clinical applications.

During the last twenty years the problem of pattern recognition (specifically, image recognition) has been studied intensively by many investigators, yet it is far from being solved. The number of publications increases yearly, but all the experimental results-with the possible exception of some dealing with recognition of printed characters-report a probability of error significantly higher than that reported for the same images by humans. It is widely agreed that ideally the recognition problem could be thought of as a problem in testing statistical hypotheses. However, in most applications the immediate use of even the simplest statistical device runs head on into grave computational difficulties, which cannot be eliminated by recourse to general theory. We must accept the fact that it is impossible to build a universal machine which can learn an arbitrary classification of multidimensional signals. Therefore the solution of the recognition problem must be based on a priori postulates (concerning the sets of signals to be recognized) that will narrow the set of possible classifications, i.e., the set of decision functions. This notion can be taken as the methodological basis for the approach adopted in this book.

This book thoroughly surveys and examines advances in fingerprint sensing devices and in algorithms for fingerprint image analysis and matching. After an opening chapter on the history of fingerprint recognition, "Automatic Fingerprint Recognition Systems" moves into new technologies for inkless sensors, fingerprint image analysis techniques, including fingerprint video analysis, filtering and classification and other areas aimed at fully automatic operation. The book also addresses large-scale fingerprint identification system design, as well as standards.

Topics and Features:

* Covers numerous areas related to modern automatic fingerprint recognition, not just its history or forensic analysis

* Examines advances in fingerprint sensing and fingerprint image filtering and preprocessing

* Describes fingerprint feature abstraction, as well as compression and decompression of fingerprint images

* Develops ideas related to large-scale, large-database fingerprint matching

* Assesses such important areas as security in fingerprint matching and the common criterion protection profile

This authoritative survey provides a unique reference for automatic fingerprint recognition concepts, technologies, and systems. Its editors and contributors are leading researchers and applied R&D developers of this technology. Biometrics and pattern recognition researchers, security professionals, and systems developers will find the work an indispensable resource for current knowledge and technology.

Human Identification Based on Gait is the first book to address gait as a biometric. Biometrics is now in a unique position where it affects most people's lives. This is especially true of "gait," which is one of the most recent biometrics. Recognizing people by the way they walk and run implies analyzing movement which, in turn, implies analyzing sequences of images, thus requiring memory and computational performance that became available only recently. Human Identification Based on Gait introduces developments from distinguished researchers within this relatively new area of biometrics. This book clearly establishes how human gait is biometric.

Human Identification Based on Gait is structured to meet the needs of professionals in industry, as well as advanced-level students in computer science.

This book constitutes the thoroughly refereed proceedings of the 17th International Conference on Discrete Geometry for Computer Imagery, DGCI 2013, held in Seville, Spain, in March 2013. The 34 revised full papers presented were carefully selected from 56 submissions and focus on geometric transforms, discrete and combinatorial tools for image segmentation and analysis, discrete and combinatorial topology, discrete shape representation, recognition and analysis, models for discrete geometry, morphological analysis and discrete tomography.

The two-volume set LNCS 7552 + 7553 constitutes the proceedings of the 22nd International Conference on Artificial Neural Networks, ICANN 2012, held in Lausanne, Switzerland, in September 2012. The 162 papers included in the proceedings were carefully reviewed and selected from 247 submissions. They are organized in topical sections named: theoretical neural computation; information and optimization; from neurons to neuromorphism; spiking dynamics; from single neurons to networks; complex firing patterns; movement and motion; from sensation to perception; object and face recognition; reinforcement learning; bayesian and echo state networks; recurrent neural networks and reservoir computing; coding architectures; interacting with the brain; swarm intelligence and decision-making; mulitlayer perceptrons and kernel networks; training and learning; inference and recognition; support vector machines; self-organizing maps and clustering; clustering, mining and exploratory analysis; bioinformatics; and time weries and forecasting.

This two-volume set LNAI 7523 and LNAI 7524 constitutes the refereed proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases: ECML PKDD 2012, held in Bristol, UK, in September 2012. The 105 revised research papers presented together with 5 invited talks were carefully reviewed and selected from 443 submissions. The final sections of the proceedings are devoted to Demo and Nectar papers. The Demo track includes 10 papers (from 19 submissions) and the Nectar track includes 4 papers (from 14 submissions). The papers grouped in topical sections on association rules and frequent patterns; Bayesian learning and graphical models; classification; dimensionality reduction, feature selection and extraction; distance-based methods and kernels; ensemble methods; graph and tree mining; large-scale, distributed and parallel mining and learning; multi-relational mining and learning; multi-task learning; natural language processing; online learning and data streams; privacy and security; rankings and recommendations; reinforcement learning and planning; rule mining and subgroup discovery; semi-supervised and transductive learning; sensor data; sequence and string mining; social network mining; spatial and geographical data mining; statistical methods and evaluation; time series and temporal data mining; and transfer learning.

The two-volume set LNCS 7552 + 7553 constitutes the proceedings of the 22nd International Conference on Artificial Neural Networks, ICANN 2012, held in Lausanne, Switzerland, in September 2012. The 162 papers included in the proceedings were carefully reviewed and selected from 247 submissions. They are organized in topical sections named: theoretical neural computation; information and optimization; from neurons to neuromorphism; spiking dynamics; from single neurons to networks; complex firing patterns; movement and motion; from sensation to perception; object and face recognition; reinforcement learning; bayesian and echo state networks; recurrent neural networks and reservoir computing; coding architectures; interacting with the brain; swarm intelligence and decision-making; mulitlayer perceptrons and kernel networks; training and learning; inference and recognition; support vector machines; self-organizing maps and clustering; clustering, mining and exploratory analysis; bioinformatics; and time weries and forecasting.

A fast and reasonably accurate perception of the environment is essential for successful navigation of an autonomous agent. Although many modes of sensing are applicable to this task and have been used, vision remains the most appealing due to its passive nature, good range, and resolution. Most vision techniques to recover depth for navigation use stereo. In the last few years, researchers have started studying techniques to combine stereo with the motion of the camera. Skifstad's dissertation proposes a new approach to recover depth information using known camera motion. This approach results in a robust technique for fast estimation of distances to objects in an image using only one translating camera. A very interesting aspect of the approach pursued by Skifstad is the method used to bypass the most difficult and computationally expensive step in using stereo or similar approaches for the vision-based depth esti mation. The correspondence problem has been the focus of research in most stereo approaches. Skifstad trades the correspondence problem for the known translational motion by using the fact that it is easier to detect single pixel disparities in a sequence of images rather than arbitrary disparities after two frames. A very attractive feature of this approach is that the computations required to detect single pixel disparities are local and hence can be easily parallelized. Another useful feature of the approach, particularly in naviga tion applications, is that the closer objects are detected earlier."