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.

The seven-volume set comprising LNCS volumes 7572-7578 constitutes the refereed proceedings of the 12th European Conference on Computer Vision, ECCV 2012, held in Florence, Italy, in October 2012. The 408 revised papers presented were carefully reviewed and selected from 1437 submissions. The papers are organized in topical sections on geometry, 2D and 3D shapes, 3D reconstruction, visual recognition and classification, visual features and image matching, visual monitoring: action and activities, models, optimisation, learning, visual tracking and image registration, photometry: lighting and colour, and image segmentation.

New to the Second Edition: offers the latest developments in standards activities (JPEG-LS, MPEG-4, MPEG-7, and H.263) provides a comprehensive review of recent activities on multimedia enhanced processors, multimedia coprocessors, and dedicated processors, including examples from industry. Image and Video Compression Standards: Algorithms and Architectures, Second Edition presents an introduction to the algorithms and architectures that form the underpinnings of the image and video compressions standards, including JPEG (compression of still-images), H.261 and H.263 (video teleconferencing), and MPEG-1 and MPEG-2 (video storage and broadcasting). The next generation of audiovisual coding standards, such as MPEG-4 and MPEG-7, are also briefly described. In addition, the book covers the MPEG and Dolby AC-3 audio coding standards and emerging techniques for image and video compression, such as those based on wavelets and vector quantization. Image and Video Compression Standards: Algorithms and Architectures, Second Edition emphasizes the foundations of these standards; namely, techniques such as predictive coding, transform-based coding such as the discrete cosine transform (DCT), motion estimation, motion compensation, and entropy coding, as well as how they are applied in the standards. The implementation details of each standard are avoided; however, the book provides all the material necessary to understand the workings of each of the compression standards, including information that can be used by the reader to evaluate the efficiency of various software and hardware implementations conforming to these standards. Particular emphasis is placed on those algorithms and architectures that have been found to be useful in practical software or hardware implementations. Image and Video Compression Standards: Algorithms and Architectures, Second Edition uniquely covers all major standards (JPEG, MPEG-1, MPEG-2, MPEG-4, H.261, H.263) in a simple and tutorial manner, while fully addressing the architectural considerations involved when implementing these standards. As such, it serves as a valuable reference for the graduate student, researcher or engineer. The book is also used frequently as a text for courses on the subject, in both academic and professional settings.

This, the 20th issue of the Transactions on Computational Science journal, edited by Bahman Kalantari, is devoted to the topic of Voronoi Diagrams and their applications. The 10 full papers included in the volume are revised and extended versions of a selection of papers presented at the International Symposium on Voronoi Diagrams 2012, held in Rutgers, NJ, USA, in June 2012. They provide an in-depth overview of current research on topological data structures and a comprehensive evaluation of their applications in the fields of cartography, physics, material modeling, chemistry, GIS, motion planning and computer graphics.

The seven-volume set comprising LNCS volumes 7572-7578 constitutes the refereed proceedings of the 12th European Conference on Computer Vision, ECCV 2012, held in Florence, Italy, in October 2012. The 408 revised papers presented were carefully reviewed and selected from 1437 submissions. The papers are organized in topical sections on geometry, 2D and 3D shapes, 3D reconstruction, visual recognition and classification, visual features and image matching, visual monitoring: action and activities, models, optimisation, learning, visual tracking and image registration, photometry: lighting and colour, and image segmentation.

The three-volume set LNCS 7510, 7511, and 7512 constitutes the refereed proceedings of the 15th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2012, held in Nice, France, in October 2012. Based on rigorous peer reviews, the program committee carefully selected 252 revised papers from 781 submissions for presentation in three volumes. The first volume includes 91 papers organized in topical sections on abdominal imaging, computer-assisted interventions and robotics; computer-aided diagnosis and planning; image reconstruction and enhancement; analysis of microscopic and optical images; computer-assisted interventions and robotics; image segmentation; cardiovascular imaging; and brain imaging: structure, function and disease evolution.

1. Provides the fundamentals of subpixel mapping technology and its applications. 2. Discusses in detail the advantages of using different subpixel mapping techniques based on remote sensing data. 3. Summarizes in a systematic way current subpixel location methods. 4. Highlights authors' achievements in subpixel mapping technology. 5. Includes case studies based on remote sensing data from USA, Italy, China, and Cambodia.

This is nothing less than a totally essential reference for engineers and researchers in any field of work that involves the use of compressed imagery. Beginning with a thorough and up-to-date overview of the fundamentals of image compression, the authors move on to provide a complete description of the JPEG2000 standard. They then devote space to the implementation and exploitation of that standard. The final section describes other key image compression systems. This work has specific applications for those involved in the development of software and hardware solutions for multimedia, internet, and medical imaging applications.

This book constitutes the refereed proceedings of the International Workshop on Augemented Environments for Computer-Assited Interventions, held in conjunction with MICCAI 2011, in Toronto, Canada, in September 2011. The 13 revised full papers presented were carefully reviewed and selected from 21 submissions. The papers cover the following topics: image registration and fusion, calibration, visualisation and 3D perception, hardware and optical design, real-time implementations, validation, clinical applications and clinical evaluation.

This book constitutes the refereed proceedings of the International Conference on Computer Vision and Graphics, ICCVG 2012, held in Warsaw, Poland, in September 2012. The 89 revised full papers presented were carefully reviewed and selected from various submissions. The papers are organized in topical sections on computer graphics, computer vision and visual surveillance.

This book constitutes the refereed proceedings of the 11th International Conference on Entertainment Computing, ICEC 2012, held in Bremen, Germany, in September 2012. The 21 full papers, 13 short papers, 16 posters, 8 demos, 4 workshops, 1 tutorial and 3 doctoral consortium submissions presented were carefully reviewed and selected from 115 submissions. The papers are organized in topical sections on story telling; serious games (learning and training); self and identity, interactive performance; mixed reality and 3D worlds; serious games (health and social); player experience; tools and methods; user interface; demonstrations; industry demonstration; harnessing collective intelligence with games; game development and model-driven software development; mobile gaming, mobile life - interweaving the virtual and the real; exploring the challenges of ethics, privacy and trust in serious gaming; open source software for entertainment.

This book constitutes the refereed proceedings of the Chinese Conference on Pattern Recognition, CCPR 2012, held in Beijing, China, in September 2012. The 82 revised full papers presented were carefully reviewed and selected from 137 submissions. The papers are organized in topical sections on pattern recognition theory; computer vision; biometric recognition; medical imaging; image and video analysis; document analysis; speech processing; natural language processing and information retrieval.

The three volume set LNAI 7506, LNAI 7507 and LNAI 7508 constitutes the refereed proceedings of the 5th International Conference on Intelligent Robotics and Applications, ICIRA 2012, held in Montreal, Canada, in October 2012. The 197 revised full papers presented were thoroughly reviewed and selected from 271 submissions. They present the state-of-the-art developments in robotics, automation and mechatronics. This volume covers the topics of robotics for rehabilitation and assistance; mechatronics and integration technology in electronics and information devices fabrication; man-machine interactions; manufacturing; micro and nano systems; mobile robots and intelligent autonomous systems; motion control; multi-agent systems and distributed control; and multi-sensor data fusion algorithms.

The five volume set LNCS 7663, LNCS 7664, LNCS 7665, LNCS 7666 and LNCS 7667 constitutes the proceedings of the 19th International Conference on Neural Information Processing, ICONIP 2012, held in Doha, Qatar, in November 2012. The 423 regular session papers presented were carefully reviewed and selected from numerous submissions. These papers cover all major topics of theoretical research, empirical study and applications of neural information processing research. The 5 volumes represent 5 topical sections containing articles on theoretical analysis, neural modeling, algorithms, applications, as well as simulation and synthesis.

Rate-Quality Optimized Video Coding discusses the matter of optimizing (or negotiating) the data rate of compressed digital video and its quality, which has been a relatively neglected topic in either side of image/video coding and tele-traffic management. Video rate management becomes a technically challenging task since it is required to maintain a certain video quality regardless of the availability of transmission or storage media. This is caused by the broadband nature of digital video and inherent algorithmic features of mainstream video compression schemes, e.g. H.261, H.263 and MPEG series. In order to maximize the media utilization and to enhance video quality, the data rate of compressed video should be regulated within a budget of available media resources while maintaining the video quality as high as possible. In Part I (Chapters 1 to 4) the non-stationarity of digital video is discussed. Since the non-stationary nature is also inherited from algorithmic properties of international video coding standards, which are a combination of statistical coding techniques, the video rate management techniques of these standards are explored. Although there is a series of known video rate control techniques, such as picture rate variation, frame dropping, etc., these techniques do not view the matter as an optimization between rate and quality. From the view of rate-quality optimization, the quantizer is the sole means of controling rate and quality. Thus, quantizers and quantizer control techniques are analyzed, based on the relationship of rate and quality. In Part II (Chapters 5 and 6), as a coherent approach to non-stationary video, established but still thriving nonlinear techniques are applied to video rate-quality optimization such as artificial neural networks including radical basis function networks, and fuzzy logic-based schemes. Conventional linear techniques are also described before the nonlinear techniques are explored. By using these nonlinear techniques, it is shown how they influence and tackle the rate-quality optimization problem. Finally, in Chapter 7 rate-quality optimization issues are reviewed in emerging video communication applications such as video transcoding and mobile video. This chapter discusses some new issues and prospects of rate and quality control in those technology areas. Rate-Quality Optimized Video Coding is an excellent reference and can be used for advanced courses on the topic.

"This book is concerned with a probabilistic approach for image analysis, mostly from the Bayesian point of view, and the important Markov chain Monte Carlo methods commonly used....This book will be useful, especially to researchers with a strong background in probability and an interest in image analysis. The author has presented the theory with rigor he doesn t neglect applications, providing numerous examples of applications to illustrate the theory." -- MATHEMATICAL REVIEWS"

This book constitutes the refereed proceedings of the 5th INNS IAPR TC3 GIRPR International Workshop on Artificial Neural Networks in Pattern Recognition, ANNPR 2012, held in Trento, Italy, in September 2012. The 21 revised full papers presented were carefully reviewed and selected for inclusion in this volume. They cover a large range of topics in the field of neural network- and machine learning-based pattern recognition presenting and discussing the latest research, results, and ideas in these areas.

The two volume set LNCS 7431 and 7432 constitutes the refereed proceedings of the 8th International Symposium on Visual Computing, ISVC 2012, held in Rethymnon, Crete, Greece, in July 2012. The 68 revised full papers and 35 poster papers presented together with 45 special track papers were carefully reviewed and selected from more than 200 submissions. The papers are organized in topical sections: Part I (LNCS 7431) comprises computational bioimaging; computer graphics; calibration and 3D vision; object recognition; illumination, modeling, and segmentation; visualization; 3D mapping, modeling and surface reconstruction; motion and tracking; optimization for vision, graphics, and medical imaging, HCI and recognition. Part II (LNCS 7432) comprises topics such as unconstrained biometrics: advances and trends; intelligent environments: algorithms and applications; applications; virtual reality; face processing and recognition.

Accurate Visual Metrology from Single and Multiple Uncalibrated Images presents novel techniques for constructing three-dimensional models from bi-dimensional images using virtual reality tools. Antonio Criminisi develops the mathematical theory of computing world measurements from single images, and builds up a hierarchy of novel, flexible techniques to make measurements and reconstruct three-dimensional scenes from uncalibrated images, paying particular attention to the accuracy of the reconstruction. This book includes examples of interesting viable applications (eg. Forensic Science, History of Art, Virtual Reality, Architectural and indoor measurements), presented in a simple way, accompanied by pictures, diagrams and plenty of worked examples to help the reader understand and implement the algorithms.

This book constitutes the thoroughly refereed proceedings of the 14th International Conference on Advanced Concepts for Intelligent Vision Systems, ACIVS 2012, held in Brno, Czech Republic, in September 2012. The 46 revised full papers were carefully selected from 81 submissions and deal with image analysis and computer vision with a focus on detection, recognition, tracking and identification.

In the design of any visual objects, the work becomes much easier if previous designs are utilized. Computer graphics is becoming increasingly important simply because it greatly helps in utilizing such previous designs. Here, "previous designs" signifies both design results and design procedures. The objects designed are diverse. For engineers, these objects could be machines or electronic circuits, as discussed in Chap. 3, ''CA~/CAM. '' Physicians often design models of a patient's organs from computed tomography images prior to surgery or to assist in diagnosis. This is the subject of Chap. 8, "Medical Graphics. " Chapter 7, "Computer Art," deals with the way in which artists use computer graphics in creating beautiful visual images. In Chap. 1, "Computational Geometry," a firm basis is provided for the definition of shapes in designed objects; this is a typical technical area in which computer graphics is constantly making worldwide progress. Thus, the present volume, reflecting international advances in these and other areas of computer graphics, provides every potential or actual graphics user with the essential up-to-date information. There are, typically, two ways of gathering this current information. One way is to invite international authorities to write on their areas of specialization. Usually this works very well if the areas are sufficiently established that it is possible to judge exactly who knows what. Since computer graphics, however, is still in its developmental stage, this method cannot be applied.

This book constitutes the refereed proceedings of the Third Knowledge Technology Week, KTW 2011, held in Kajang, Malaysia, in July 2011. The 29 revised full papers presented together with 9 short papers were carefully reviewed and selected from 105 submissions. KTW 2011 consisted of a number of co-located events. This volume contains selected papers from the proceedings of the Third Malaysian Joint Conference on Artificial Intelligence (MJCAI 2011), the Third Semantic Technology and Knowledge Engineering (STAKE 2011), and the International Workshop on Semantic Agents (IWSA 2012).

This book includes the thoroughly refereed post-conference proceedings of the 15th Annual RoboCup International Symposium, held in Istanbul, Turkey, in July 2011. The 12 revised papers and 32 poster presentation presented were carefully reviewed and selected from 97 submissions. The papers are orginazed on topical sections on robot hardware and software, perception and action, robotic cognition and learning, multi-robot systems, human-robot interaction, education and edutainment and applications.

Stochastic Image Processing provides the first thorough treatment of Markov and hidden Markov random fields and their application to image processing. Although promoted as a promising approach for over thirty years, it has only been in the past few years that the theory and algorithms have developed to the point of providing useful solutions to old and new problems in image processing. Markov random fields are a multidimensional extension of Markov chains, but the generalization is complicated by the lack of a natural ordering of pixels in multidimensional spaces. Hidden Markov fields are a natural generalization of the hidden Markov models that have proved essential to the development of modern speech recognition, but again the multidimensional nature of the signals makes them inherently more complicated to handle. This added complexity contributed to the long time required for the development of successful methods and applications. This book collects together a variety of successful approaches to a complete and useful characterization of multidimensional Markov and hidden Markov models along with applications to image analysis. The book provides a survey and comparative development of an exciting and rapidly evolving field of multidimensional Markov and hidden Markov random fields with extensive references to the literature.

This book contains the papers presented at the NATO Advanced Study Institute (ASI) on the Basics of Man-Machine Communication for the Design of Educational Systems, held August 16-26, 1993 in Eindhoven, The Netherlands. The ASI addressed the state of the art in the design of educational systems with respect to theories, enabling technologies and advanced applications and implementation issues. The topics discussed are grouped into four main subject areas: 1) Fundamentals of human perception and reasoning, 2) New media: enabling technologies, 3) Artificial Intelligence; software and design techniques, and 4) Advanced applications. This interdisciplinary approach, with a clear focus on the application domain of learning environments, provided the platform for interdisciplinary exchange and communication between the participants. The role of human perception and reasoning was presented in the context of design requirements. The construction of usable human-machine interfaces requires designers to be aware of the inherent competence of the human user. That is, a designer needs to understand the resources that the user brings to the interaction. This includes the general nature of human and world interactions; the nature of the human perceptual system; the natural learning processes by which the information given by the senses is transformed into knowledge of the world; the reasoning processes that allow humans to make inferences from that knowledge once acquired; and the ways in which acquired knowledge may be communicated to others through language.