The two volumes LNCS 6553 and 6554 constitute the refereed post-proceedings of 7 workshops held in conjunction with the 11th European Conference on Computer Vision, held in Heraklion, Crete, Greece in September 2010. The 62 revised papers presented together with 2 invited talks were carefully reviewed and selected from numerous submissions. The first volume contains 26 revised papers and 2 invited talks selected from the following workshops: First International Workshop on Parts and Attributes; Third Workshop on Human Motion Understanding, Modeling, Capture and Animation; and International Workshop on Sign, Gesture and Activity (SGA 2010).

This volume contains the proceedings of the NATO Advanced Study Institute on "Pictorial Information Systems in Medicine" held August 27-September 7, 1984 in Hotel Maritim, Braunlage/Harz, Federal Republic of Germany. The program committee of the institute consisted of KH Hohne (Director), G. T Herman, G. S. Lodwick, and D. Meyer-Ebrecht. The organization was in the hands of Klaus Assmann and Fritz Bocker In the last decade medical imaging has undergone a rapid development New imaging modalities such as Computer Tomography (CT), Digital Angiography (DSA) and Magnetic Resonance Imaging (MRI) were developed using the capabilities of modern computers. In a modern hospital these technologies produce already more then 25% of image data in digital form. This format lends itself to the design of computer assisted Information systems Integrating data acquisition, presentation, communi cation and archiving for all modalities and users within a department or even a hospital. Advantages such as rapid access to any archived Image, synoptic presentation, computer assisted image analysis to name only a few, are expected. The design of such pictorial information systems, however, often called PACS (Picture Archiving and Communication Systems) In the medical community is a non-trivial task involving know-how from many disciplines such as - Medicine (especially Radiology), - Data Base Technology, - Computer Graphics, - Man Machine Interaction, - Hardware Technology and others. Most of these disCiplines are represented by disjunct scientific communities."

About four or five years ago one began to hear about the enormous interest being taken in on-line consoles and displays. Nothing much was done with them, but computer men felt that this was the way computing ought to go: one might dispense with cards, and overcome many of the problems of man-machine communication. It quickly appeared that, as with computers, there had been a great under estimation of the amount of work involved, of the difficulties of programming, and of the cost. So it began to emerge that graphics was not the ultimate answer, in spite of superb demonstrations where one might watch a square being converted into a cube and then rotated. But my mind goes back to 1951 and the first computers. There, there were demonstrations of arithmetic speed and storage facility; but not much idea of actual use. However, we now understand how to use computers, and in the last year or two, significant developments in the field of graphics have led to genuine applications, and economic benefits. The equipment is still expensive, but it is becoming cheaper, more uses are being found, and f believe that we are just at the stage when the subject is gaining momentum, to become, like computers, a field of immense importance."

Techniques of vision-based motion analysis aim to detect, track, identify, and generally understand the behavior of objects in image sequences. With the growth of video data in a wide range of applications from visual surveillance to human-machine interfaces, the ability to automatically analyze and understand object motions from video footage is of increasing importance. Among the latest developments in this field is the application of statistical machine learning algorithms for object tracking, activity modeling, and recognition.

Developed from expert contributions to the first and second International Workshop on Machine Learning for Vision-Based Motion Analysis, this important text/reference highlights the latest algorithms and systems for robust and effective vision-based motion understanding from a machine learning perspective. Highlighting the benefits of collaboration between the communities of object motion understanding and machine learning, the book discusses the most active forefronts of research, including current challenges and potential future directions.

Topics and features: provides a comprehensive review of the latest developments in vision-based motion analysis, presenting numerous case studies on state-of-the-art learning algorithms; examines algorithms for clustering and segmentation, and manifold learning for dynamical models; describes the theory behind mixed-state statistical models, with a focus on mixed-state Markov models that take into account spatial and temporal interaction; discusses object tracking in surveillance image streams, discriminative multiple target tracking, and guidewire tracking in fluoroscopy; explores issues of modeling for saliency detection, human gait modeling, modeling of extremely crowded scenes, and behavior modeling from video surveillance data; investigates methods for automatic recognition of gestures in Sign Language, and human action recognition from small training sets.

Researchers, professional engineers, and graduate students in computer vision, pattern recognition and machine learning, will all find this text an accessible survey of machine learning techniques for vision-based motion analysis. The book will also be of interest to all who work with specific vision applications, such as surveillance, sport event analysis, healthcare, video conferencing, and motion video indexing and retrieval.

Parallel processing is seen today as the means to improve the power of computing facilities by breaking the Von Neumann bottleneck of conventional sequential computer architectures. By defining appropriate parallel computation models definite advantages can be obtained. Parallel processing is the center of the research in Europe in the field of Information Processing Systems so the CEC has funded the ESPRIT Supemode project to develop a low cost, high performance, multiprocessor machine. The result of this project is a modular, reconfigurable architecture based on !NMOS transputers: T.Node. This machine can be considered as a research, industrial and commercial success. The CEC has decided to continue to encourage manufacturers as well as research and end-users of transputers by funding other projects in this field. This book presents course papers of the Eurocourse given at the Joint Research Centre in ISPRA (Italy) from the 4th to 8 of November 1991. First we present an overview of various trends in the design of parallel architectures and specially of the T.Node with it's software development environments, new distributed system aspects and also new hardware extensions based on the !NMOS T9000 processor. In a second part, we review some real case applications in the field of image synthesis, image processing, signal processing, terrain modeling, particle physics simulation and also enhanced parallel and distributed numerical methods on T.Node.

Alias|Wavefront's Maya 3D animation software is an integrated collection of tools for creating computer generated images, used in nearly every blockbuster special effects film that has been released in the last few years. The first choice for digital content creators, Maya combines animation, dynamics, modelling and rendering tools, enabling you to create digital characters and visual effects for live action films or stand-alone animation.

Machine vision technology has revolutionised the process of automated inspection in manufacturing. The specialist techniques required for inspection of natural products, such as food, leather, textiles and stone is still a challenging area of research. Topological variations make image processing algorithm development, system integration and mechanical handling issues much more complex. The practical issues of making machine vision systems operate robustly in often hostile environments together with the latest technological advancements are reviewed in this volume. Features: - Case studies based on real-world problems to demonstrate the practical application of machine vision systems. - In-depth description of system components including image processing, illumination, real-time hardware, mechanical handling, sensing and on-line testing. - Systems-level integration of constituent technologies for bespoke applications across a variety of industries. - A diverse range of example applications that a system may be required to handle from live fish to ceramic tiles. Machine Vision for the Inspection of Natural Products will be a valuable resource for researchers developing innovative machine vision systems in collaboration with food technology, textile and agriculture sectors. It will also appeal to practising engineers and managers in industries where the application of machine vision can enhance product safety and process efficiency.

Biological visual systems employ massively parallel processing to perform real-world visual tasks in real time. A key to this remarkable performance seems to be that biological systems construct representations of their visual image data at multiple scales. A Pyramid Framework for Early Vision describes a multiscale, or 'pyramid', approach to vision, including its theoretical foundations, a set of pyramid-based modules for image processing, object detection, texture discrimination, contour detection and processing, feature detection and description, and motion detection and tracking. It also shows how these modules can be implemented very efficiently on hypercube-connected processor networks. A Pyramid Framework for Early Vision is intended for both students of vision and vision system designers; it provides a general approach to vision systems design as well as a set of robust, efficient vision modules.

With the ubiquity of new information technology and media, more effective and friendly methods for human computer interaction (HCI) are being developed which do not rely on traditional devices such as keyboards, mice and displays. The first step for any intelligent HCI system is face detection, and one of most friendly HCI systems is hand gesture. Face Detection and Gesture Recognition for Human-Computer Interaction introduces the frontiers of vision-based interfaces for intelligent human computer interaction with focus on two main issues: face detection and gesture recognition. The first part of the book reviews and discusses existing face detection methods, followed by a discussion on future research. Performance evaluation issues on the face detection methods are also addressed. The second part discusses an interesting hand gesture recognition method based on a generic motion segmentation algorithm. The system has been tested with gestures from American Sign Language with promising results. We conclude this book with comments on future work in face detection and hand gesture recognition.Face Detection and Gesture Recognition for Human-Computer Interaction will interest those working in vision-based interfaces for intelligent human computer interaction. It also contains a comprehensive survey on existing face detection methods, which will serve as the entry point for new researchers embarking on such topics. Furthermore, this book also covers in-depth discussion on motion segmentation algorithms and applications, which will benefit more seasoned graduate students or researchers interested in motion pattern recognition.

Traditionally, scientific fields have defined boundaries, and scientists work on research problems within those boundaries. However, from time to time those boundaries get shifted or blurred to evolve new fields. For instance, the original goal of computer vision was to understand a single image of a scene, by identifying objects, their structure, and spatial arrangements. This has been referred to as image understanding. Recently, computer vision has gradually been making the transition away from understanding single images to analyz ing image sequences, or video understanding. Video understanding deals with understanding of video sequences, e. g. , recognition of gestures, activities, fa cial expressions, etc. The main shift in the classic paradigm has been from the recognition of static objects in the scene to motion-based recognition of actions and events. Video understanding has overlapping research problems with other fields, therefore blurring the fixed boundaries. Computer graphics, image processing, and video databases have obvious overlap with computer vision. The main goal of computer graphics is to gener ate and animate realistic looking images, and videos. Researchers in computer graphics are increasingly employing techniques from computer vision to gen erate the synthetic imagery. A good example of this is image-based rendering and modeling techniques, in which geometry, appearance, and lighting is de rived from real images using computer vision techniques. Here the shift is from synthesis to analysis followed by synthesis.

Advances in electronics, communications, and the fast growth of the Internet have made the use of a wide variety of computing devices an every day occurrence. These computing devices have different interaction styles, input/output techniques, modalities, characteristics, and contexts of use. Furthermore, users expect to access their data and run the same application from any of these devices. Two of the problems we encountered in our own work [2] in building VIs for different platforms were the different layout features and screen sizes associated with each platform and device. Dan Ol sen [13], Peter Johnson [9], and Stephen Brewster, et al. [4] all talk about problems in interaction due to the diversity of interactive platforms, devices, network services and applications. They also talk about the problems associ ated with the small screen size of hand-held devices. In comparison to desk top computers, hand-held devices will always suffer from a lack of screen real estate, so new metaphors of interaction have to be devised for such de vices. It is difficult to develop a multi-platform user interface (VI) without duplicating development effort. Developers now face the daunting task to build UIs that must work across multiple devices. There have been some ap proaches towards solving this problem of multi-platform VI development in cluding XWeb [14]. Building "plastic interfaces" [5,20] is one such method in which the VIs are designed to "withstand variations of context of use while preserving usability".

Data Management and Internet Computing for Image/Pattern Analysis focuses on the data management issues and Internet computing aspect of image processing and pattern recognition research. The book presents a comprehensive overview of the state of the art, providing detailed case studies that emphasize how image and pattern (IAP) data are distributed and exchanged on sequential and parallel machines, and how the data communication patterns in low- and higher-level IAP computing differ from general numerical computation, what problems they cause and what opportunities they provide. The studies also describe how the images and matrices should be stored, accessed and distributed on different types of machines connected to the Internet, and how Internet resource sharing and data transmission change traditional IAP computing. Data Management and Internet Computing for Image/Pattern Analysis is divided into three parts: the first part describes several software approaches to IAP computing, citing several representative data communication patterns and related algorithms; the second part introduces hardware and Internet resource sharing in which a wide range of computer architectures are described and memory management issues are discussed; and the third part presents applications ranging from image coding, restoration and progressive transmission. Data Management and Internet Computing for Image/Pattern Analysis is an excellent reference for researchers and may be used as a text for advanced courses in image processing and pattern recognition.

The last few years have seen a great increase in the amount of data available to scientists, yet many of the techniques used to analyse this data cannot cope with such large datasets. Therefore, strategies need to be employed as a pre-processing step to reduce the number of objects or measurements whilst retaining important information. Spectral dimensionality reduction is one such tool for the data processing pipeline. Numerous algorithms and improvements have been proposed for the purpose of performing spectral dimensionality reduction, yet there is still no gold standard technique. This book provides a survey and reference aimed at advanced undergraduate and postgraduate students as well as researchers, scientists, and engineers in a wide range of disciplines. Dimensionality reduction has proven useful in a wide range of problem domains and so this book will be applicable to anyone with a solid grounding in statistics and computer science seeking to apply spectral dimensionality to their work.

Semantic Video Object Segmentation for Content-Based Multimedia Applications provides a thorough review of state-of-the-art techniques as well as describing several novel ideas and algorithms for semantic object extraction from image sequences. Semantic object extraction is an essential element in content-based multimedia services, such as the newly developed MPEG4 and MPEG7 standards. An interactive system called SIVOG (Smart Interactive Video Object Generation) is presented, which converts user's semantic input into a form that can be conveniently integrated with low-level video processing. Thus, high-level semantic information and low-level video features are integrated seamlessly into a smart segmentation system. A region and temporal adaptive algorithm was further proposed to improve the efficiency of the SIVOG system so that it is feasible to achieve nearly real-time video object segmentation with robust and accurate performances. Also included is an examination of the shape coding problem and the object segmentation problem simultaneously. Semantic Video Object Segmentation for Content-Based Multimedia Applications will be of great interest to research scientists and graduate-level students working in the area of content-based multimedia representation and applications and its related fields.

Computer and Information Sciences is a unique and comprehensive review of advanced technology and research in the field of Information Technology. It provides an up to date snapshot of research in Europe and the Far East (Hong Kong, Japan and China) in the most active areas of information technology, including Computer Vision, Data Engineering, Web Engineering, Internet Technologies, Bio-Informatics and System Performance Evaluation Methodologies.

Consumer electronics (CE) devices, providing multimedia entertainment and enabling communication, have become ubiquitous in daily life. However, consumer interaction with such equipment currently requires the use of devices such as remote controls and keyboards, which are often inconvenient, ambiguous and non-interactive. An important challenge for the modern CE industry is the design of user interfaces for CE products that enable interactions which are natural, intuitive and fun. As many CE products are supplied with microphones and cameras, the exploitation of both audio and visual information for interactive multimedia is a growing field of research. Collecting together contributions from an international selection of experts, including leading researchers in industry, this unique text presents the latest advances in applications of multimedia interaction and user interfaces for consumer electronics. Covering issues of both multimedia content analysis and human-machine interaction, the book examines a wide range of techniques from computer vision, machine learning, audio and speech processing, communications, artificial intelligence and media technology. Topics and features: introduces novel computationally efficient algorithms to extract semantically meaningful audio-visual events; investigates modality allocation in intelligent multimodal presentation systems, taking into account the cognitive impacts of modality on human information processing; provides an overview on gesture control technologies for CE; presents systems for natural human-computer interaction, virtual content insertion, and human action retrieval; examines techniques for 3D face pose estimation, physical activity recognition, and video summary quality evaluation; discusses the features that characterize the new generation of CE and examines how web services can be integrated with CE products for improved user experience. This book is an essential resource for researchers and practitioners from both academia and industry working in areas of multimedia analysis, human-computer interaction and interactive user interfaces. Graduate students studying computer vision, pattern recognition and multimedia will also find this a useful reference.

Brain imaging brings together the technology, methodology, research questions and approaches of a wide range of scientific fields including physics, statistics, computer science, neuroscience, biology, and engineering. Thus, methodological and technological advances that enable us to obtain measurements, examine relationships across observations, and link these data to neuroscientific hypotheses happen in a highly interdisciplinary environment. The dynamic field of machine learning with its modern approach to data mining provides many relevant approaches for neuroscience and enables the exploration of open questions. This state-of-the-art survey offers a collection of papers from the Workshop on Machine Learning and Interpretation in Neuroimaging, MLINI 2011, held at the 25th Annual Conference on Neural Information Processing, NIPS 2011, in the Sierra Nevada, Spain, in December 2011. Additionally, invited speakers agreed to contribute reviews on various aspects of the field, adding breadth and perspective to the volume. The 32 revised papers were carefully selected from 48 submissions. At the interface between machine learning and neuroimaging the papers aim at shedding some light on the state of the art in this interdisciplinary field. They are organized in topical sections on coding and decoding, neuroscience, dynamcis, connectivity, and probabilistic models and machine learning.

The one instruction set computer (OISC) is the ultimate reduced instruction set computer (RISC). In OISC, the instruction set consists of only one instruction, and then by composition, all other necessary instructions are synthesized. This is an approach completely opposite to that of a complex instruction set computer (CISC), which incorporates complex instructions as microprograms within the processor. Computer Architecture: A Minimalist Perspective examines computer architecture, computability theory, and the history of computers from the perspective of one instruction set computing - a novel approach in which the computer supports only one, simple instruction. This bold, new paradigm offers significant promise in biological, chemical, optical, and molecular scale computers. Features include: - Provides a comprehensive study of computer architecture using computability theory as a base. - Provides a fresh perspective on computer architecture not found in any other text. - Covers history, theory, and practice of computer architecture from a minimalist perspective. Includes a complete implementation of a one instruction computer.- Includes exercises and programming assignments. Computer Architecture: A Minimalist Perspective is designed to meet the needs of a professional audience composed of researchers, computer hardware engineers, software engineers computational theorists, and systems engineers. The book is also intended for use in upper division undergraduate students and early graduate students studying computer architecture or embedded systems. It is an excellent text for use as a supplement or alternative in traditional Computer Architecture Courses, or in courses entitled Special Topics in Computer Architecture.

This uniquely authoritative and comprehensive handbook is the first to cover the vast field of formal languages, as well as its traditional and most recent applications to such diverse areas as linguistics, developmental biology, computer graphics, cryptology, molecular genetics, and programming languages. No other work comes even close to the scope of this one. The editors are extremely well-known theoretical computer scientists, and each individual topic is presented by the leading authorities in the particular field. The maturity of the field makes it possible to include a historical perspective in many presentations. The work is divided into three volumes, which may be purchased as a set.

This volume constitutes the refereed proceedings of the Second International Conference on Multimedia and Signal Processing, CMSP 2012, held in Shanghai, China, in December 2012. The 79 full papers included in the volume were selected from 328 submissions from 10 different countries and regions. The papers are organized in topical sections on computer and machine vision, feature extraction, image enhancement and noise filtering, image retrieval, image segmentation, imaging techniques & 3D imaging, pattern recognition, multimedia systems, architecture, and applications, visualization, signal modeling, identification & prediction, speech & language processing, time-frequency signal analysis.

Computer systems that analyze images are critical to a wide variety of applications such as visual inspections systems for various manufacturing processes, remote sensing of the environment from space-borne imaging platforms, and automatic diagnosis from X-rays and other medical imaging sources. Professor Azriel Rosenfeld, the founder of the field of digital image analysis, made fundamental contributions to a wide variety of problems in image processing, pattern recognition and computer vision. Professor Rosenfeld's previous students, postdoctoral scientists, and colleagues illustrate in Foundations of Image Understanding how current research has been influenced by his work as the leading researcher in the area of image analysis for over two decades. Each chapter of Foundations of Image Understanding is written by one of the world's leading experts in his area of specialization, examining digital geometry and topology (early research which laid the foundations for many industrial machine vision systems), edge detection and segmentation (fundamental to systems that analyze complex images of our three-dimensional world), multi-resolution and variable resolution representations for images and maps, parallel algorithms and systems for image analysis, and the importance of human psychophysical studies of vision to the design of computer vision systems. Professor Rosenfeld's chapter briefly discusses topics not covered in the contributed chapters, providing a personal, historical perspective on the development of the field of image understanding. Foundations of Image Understanding is an excellent source of basic material for both graduate students entering the field and established researchers who require a compact source for many of the foundational topics in image analysis.

This book constitutes the proceedings of the First International Conference on Intelligent Robotics and Manufacturing, IRAM 2012, held in Kuala Lumpur, Malaysia, in November 2012. The 64 revised full papers included in this volume were carefully reviewed and selected from 102 initial submissions. The papers are organized in topical sections named: mobile robots, intelligent autonomous systems, robot vision and robust, autonomous agents, micro, meso and nano-scale automation and assembly, flexible manufacturing systems, CIM and micro-machining, and fabrication techniques.

With a preface by Ton Kalker. Informed Watermarking is an essential tool for both academic and professional researchers working in the areas of multimedia security, information embedding, and communication. Theory and practice are linked, particularly in the area of multi-user communication. From the Preface: Watermarking has become a more mature discipline with proper foundation in both signal processing and information theory. We can truly say that we are in the era of second generation watermarking. This book is first in addressing watermarking problems in terms of second-generation insights. It provides a complete overview of the most important results on capacity and security. The Costa scheme, and in particular a simpler version of it, the Scalar Costa scheme, is studied in great detail. An important result of this book is that it is possible to approach the Shannon limit within a few decibels in a practical system. These results are verified on real-world data, not only the classical category of images, but also on chemical structure sets.Inspired by the work of Moulin and O'Sullivan, this book also addresses security aspects by studying AGWN attacks in terms of game theory. The authors of Informed Watermarking give a well-written expose of how watermarking came of age, where we are now, and what to expect in the future. It is my expectation that this book will be a standard reference on second-generation watermarking for the years to come. Ton Kalker, Technische Universiteit Eindhoven

Traditionally, scientific fields have defined boundaries, and scientists work on research problems within those boundaries. However, from time to time those boundaries get shifted or blurred to evolve new fields. For instance, the original goal of computer vision was to understand a single image of a scene, by identifying objects, their structure, and spatial arrangements. This has been referred to as image understanding. Recently, computer vision has gradually been making the transition away from understanding single images to analyz ing image sequences, or video understanding. Video understanding deals with understanding of video sequences, e. g. , recognition of gestures, activities, fa cial expressions, etc. The main shift in the classic paradigm has been from the recognition of static objects in the scene to motion-based recognition of actions and events. Video understanding has overlapping research problems with other fields, therefore blurring the fixed boundaries. Computer graphics, image processing, and video databases have obvious overlap with computer vision. The main goal of computer graphics is to gener ate and animate realistic looking images, and videos. Researchers in computer graphics are increasingly employing techniques from computer vision to gener ate the synthetic imagery. A good example of this is image-based rendering and modeling techniques, in which geometry, appearance, and lighting is de rived from real images using computer vision techniques. Here the shift is from synthesis to analysis followed by synthesis.

Data visualization is currently a very active and vital area of research, teaching and development. The term unites the established field of scientific visualization and the more recent field of information visualization. The success of data visualization is due to the soundness of the basic idea behind it: the use of computer-generated images to gain insight and knowledge from data and its inherent patterns and relationships. A second premise is the utilization of the broad bandwidth of the human sensory system in steering and interpreting complex processes, and simulations involving data sets from diverse scientific disciplines and large collections of abstract data from many sources.
These concepts are extremely important and have a profound and widespread impact on the methodology of computational science and engineering, as well as on management and administration. The interplay between various application areas and their specific problem solving visualization techniques is emphasized in this book. Reflecting the heterogeneous structure of Data Visualization, emphasis was placed on these topics:

-Visualization Algorithms and Techniques;
-Volume Visualization;
-Information Visualization;
-Multiresolution Techniques;
-Interactive Data Exploration.

Data Visualization: The State of the Art" "presents the state of the art in scientific and information visualization techniques by experts in this field. It can serve as an overview for the inquiring scientist, and as a basic foundation for developers. This edited volume contains chapters dedicated to surveys of specific topics, and a great deal of original work not previously published illustrated by examples from a wealth of applications. The book will also provide basic material for teaching the state of the art techniques in data visualization.

Data Visualization: The State of the Art is designed to meet the needs of practitioners and researchers in scientific and information visualization. This book is also suitable as a secondary text for graduate level students in computer science and engineering.