This book presents theories and techniques for perception of textures by computer. Texture is a homogeneous visual pattern that we perceive in surfaces of objects such as textiles, tree barks or stones. Texture analysis is one of the first important steps in computer vision since texture provides important cues to recognize real-world objects. A major part of the book is devoted to two-dimensional analysis of texture patterns by extracting statistical and structural features. It also deals with the shape-from-texture problem which addresses recovery of the three-dimensional surface shapes based on the geometry of projection of the surface texture to the image plane. Perception is still largely mysterious. Realizing a computer vision system that can work in the real world requires more research and ex periment. Capability of textural perception is a key component. We hope this book will contribute to the advancement of computer vision toward robust, useful systems. vVe would like to express our appreciation to Professor Takeo Kanade at Carnegie Mellon University for his encouragement and help in writing this book; to the members of Computer Vision Section at Electrotechni cal Laboratory for providing an excellent research environment; and to Carl W. Harris at Kluwer Academic Publishers for his help in preparing the manuscript."

This monograph is a revised version of the D.Phil. thesis of the first author, submitted in October 1990 to the University of Oxford. This work investigates the problem of mobile robot navigation using sonar. We view model-based navigation as a process of tracking naturally occurring environment features, which we refer to as "targets". Targets that have been predicted from the environment map are tracked to provide that are observed, but not predicted, vehicle position estimates. Targets represent unknown environment features or obstacles, and cause new tracks to be initiated, classified, and ultimately integrated into the map. Chapter 1 presents a brief definition of the problem and a discussion of the basic research issues involved. No attempt is made to survey ex haustively the mobile robot navigation literature-the reader is strongly encouraged to consult other sources. The recent collection edited by Cox and Wilfong [34] is an excellent starting point, as it contains many of the standard works of the field. Also, we assume familiarity with the Kalman filter. There are many well-known texts on the subject; our notation derives from Bar-Shalom and Fortmann [7]. Chapter 2 provides a detailed sonar sensor model. A good sensor model of our approach to navigation, and is used both for is a crucial component predicting expected observations and classifying unexpected observations.

In June 1998 the Fourth International Workshop on Digital Mammography was held in Nijmegen, The Netherlands, where it was hosted by the department of Radiology of the University Hospital Nijmegen. This series of meetings was initiated at the 1993 SPIE Biomedical Image Processing Conference in San Jose, USA, where a number of sessions were entirely devoted to mammographic image analysis. At very successful subsequent workshops held in York, UK (1994) and Chicago, USA (1996), the scope of the conference was broadened, establishing a platform for presentation and discussion of new developments in digital mammog raphy. Topics that are addressed at these meetings are computer-aided diagnosis, image processing, detector development, system design, observer performance and clinical evaluation. The goal is to bring researchers from universities, breast cancer experts, and engineers together, to exchange information and present new scientific developments in this rapidly evolving field. This book contains all the scientific papers and posters presented at the work shop in Nijmegen. Contributions came from as many as 20 different countries and 190 participants attended the meeting. At a technical exhibit companies demon strated new products and work in progress. Abstracts of all papers were reviewed by members of the scientific committee. Many of the accepted papers had excellent quality, but due to limited space not all of them could be included as full papers in these proceedings. Papers that were rated high by the reviewers are included as long or short papers, others appear as extended abstracts in the last chapter.

Current research in Visual Database Systems can be characterized by scalability, multi-modality of interaction, and higher semantic levels of data. Visual interfaces that allow users to interact with large databases must scale to web and distributed applications. Interaction with databases must employ multiple and more diversified interaction modalities, such as speech and gesture, in addition to visual exploitation. Finally, the basic elements managed in modern databases are rapidly evolving, from text, images, sound, and video, to compositions and now annotations of these media, thus incorporating ever-higher levels and different facets of semantics. In addition to visual interfaces and multimedia databases, Visual and Multimedia Information Management includes research in the following areas: * Speech and aural interfaces to databases; * Visualization of web applications and database structure; * Annotation and retrieval of image databases; * Visual querying in geographical information systems; * Video databases; and * Virtual environment and modeling of complex shapes.Visual and Multimedia Information Management comprises the proceedings of the sixth International Conference on Visual Database Systems, which was sponsored by the International Federation for Information Processing (IFIP), and held in Brisbane, Australia, in May 2002. This volume will be essential for researchers in the field of management of visual and multimedia information, as well as for industrial practitioners concerned with building IT products for managing visual and multimedia information.

This book is an introduction to the fundamental concepts and tools needed for solving problems of a geometric nature using a computer. It attempts to fill the gap between standard geometry books, which are primarily theoretical, and applied books on computer graphics, computer vision, robotics, or machine learning. This book covers the following topics: affine geometry, projective geometry, Euclidean geometry, convex sets, SVD and principal component analysis, manifolds and Lie groups, quadratic optimization, basics of differential geometry, and a glimpse of computational geometry (Voronoi diagrams and Delaunay triangulations). Some practical applications of the concepts presented in this book include computer vision, more specifically contour grouping, motion interpolation, and robot kinematics. In this extensively updated second edition, more material on convex sets, Farkas's lemma, quadratic optimization and the Schur complement have been added. The chapter on SVD has been greatly expanded and now includes a presentation of PCA. The book is well illustrated and has chapter summaries and a large number of exercises throughout. It will be of interest to a wide audience including computer scientists, mathematicians, and engineers. Reviews of first edition: "Gallier's book will be a useful source for anyone interested in applications of geometrical methods to solve problems that arise in various branches of engineering. It may help to develop the sophisticated concepts from the more advanced parts of geometry into useful tools for applications." (Mathematical Reviews, 2001) "...it will be useful as a reference book for postgraduates wishing to find the connection between their current problem and the underlying geometry." (The Australian Mathematical Society, 2001)

Mathematical morphology is a powerful methodology for the processing and analysis of geometric structure in signals and images. This book contains the proceedings of the fifth International Symposium on Mathematical Morphology and its Applications to Image and Signal Processing, held June 26-28, 2000, at Xerox PARC, Palo Alto, California. It provides a broad sampling of the most recent theoretical and practical developments of mathematical morphology and its applications to image and signal processing. Areas covered include: decomposition of structuring functions and morphological operators, morphological discretization, filtering, connectivity and connected operators, morphological shape analysis and interpolation, texture analysis, morphological segmentation, morphological multiresolution techniques and scale-spaces, and morphological algorithms and applications. Audience: The subject matter of this volume will be of interest to electrical engineers, computer scientists, and mathematicians whose research work is focused on the theoretical and practical aspects of nonlinear signal and image processing. It will also be of interest to those working in computer vision, applied mathematics, and computer graphics.

Machine Learning: Discriminative and Generative covers the main contemporary themes and tools in machine learning ranging from Bayesian probabilistic models to discriminative support-vector machines. However, unlike previous books that only discuss these rather different approaches in isolation, it bridges the two schools of thought together within a common framework, elegantly connecting their various theories and making one common big-picture. Also, this bridge brings forth new hybrid discriminative-generative tools that combine the strengths of both camps. This book serves multiple purposes as well. The framework acts as a scientific breakthrough, fusing the areas of generative and discriminative learning and will be of interest to many researchers. However, as a conceptual breakthrough, this common framework unifies many previously unrelated tools and techniques and makes them understandable to a larger portion of the public. This gives the more practical-minded engineer, student and the industrial public an easy-access and more sensible road map into the world of machine learning. Machine Learning: Discriminative and Generative is designed for an audience composed of researchers & practitioners in industry and academia. The book is also suitable as a secondary text for graduate-level students in computer science and engineering.

Analyzing Video Sequences of Multiple Humans: Tracking, Posture Estimation and Behavior Recognition describes some computer vision-based methods that analyze video sequences of humans. More specifically, methods for tracking multiple humans in a scene, estimating postures of a human body in 3D in real-time, and recognizing a person's behavior (gestures or activities) are discussed. For the tracking algorithm, the authors developed a non-synchronous method that tracks multiple persons by exploiting a Kalman filter that is applied to multiple video sequences. For estimating postures, an algorithm is presented that locates the significant points which determine postures of a human body, in 3D in real-time. Human activities are recognized from a video sequence by the HMM (Hidden Markov Models)-based method that the authors pioneered. The effectiveness of the three methods is shown by experimental results.

This book presents key machine vision techniques and algorithms, along with the associated Java source code. Special features include a complete self-contained treatment of all topics and techniques essential to the understanding and implementation of machine vision; an introduction to object-oriented programming and to the Java programming language, with particular reference to its imaging capabilities; Java source code for a wide range of real-world image processing and analysis functions; an introduction to the Java 2D imaging and Java Advanced Imaging (JAI) API; and a wide range of illustrative examples.

This book constitutes revised selected papers from the 9th International Gesture Workshop, GW 2011, held in Athens, Greece, in May 2011. The 24 papers presented were carefully reviewed and selected from 35 submissions. They are ordered in five sections named: human computer interaction; cognitive processes; notation systems and animation; gestures and signs: linguistic analysis and tools; and gestures and speech.

Mathematical morphology (MM) is a theory for the analysis of spatial structures. It is called morphology since it aims at analysing the shape and form of objects, and it is mathematical in the sense that the analysis is based on set theory, topology, lattice algebra, random functions, etc. MM is not only a theory, but also a powerful image analysis technique. The purpose of the present book is to provide the image analysis community with a snapshot of current theoretical and applied developments of MM. The book consists of forty-five contributions classified by subject. It demonstrates a wide range of topics suited to the morphological approach.

Vision chips, or smart visual sensors, are those sensors that have integrated image acquisition and parallel processing, often at the pixel level, using dedicated analog and digital circuits. Vision Chips presents a systematic approach to the design and analysis of vision chips using analog VLSL. * It presents algorithmic level implementation issues, from both the VLSI and computer vision points of view. * It reviews the VLSI technologies and general analog VLSI design methodologies, in the context of suitability for vision chips. * It describes chip-level architectural issues, including tessellation structures, pixel-processor interaction, and data read-out. * It presents detailed analysis of building-blocks necessary in vision chips, including photodetectors, photocircuits, and spatial and temporal processing circuits. * It addresses other important design issues, such as testing, digital noise, and mismatch. In addition Vision Chips reviews some of the past and existing implementations of smart vision sensors. It contains condensed information on more than fifty vision chips, designed by research laboratories all over the world.Novel and interesting features of each vision chip have been highlighted through informative diagrams and concise descriptions. This book is a valuable asset for researchers in the area, engineers working on the design of vision sensors, graduate students working in analog VLSI and vision, and computer vision and biological vision researchers and scientists.

Fourier Vision provides a new treatment of figure-ground segmentation in scenes comprising transparent, translucent, or opaque objects. Exploiting the relative motion between figure and ground, this technique deals explicitly with the separation of additive signals and makes no assumptions about the spatial or spectral content of the images, with segmentation being carried out phasor by phasor in the Fourier domain. It works with several camera configurations, such as camera motion and short-baseline binocular stereo, and performs best on images with small velocities/displacements, typically one to ten pixels per frame. The book also addresses the use of Fourier techniques to estimate stereo disparity and optical flow. Numerous examples are provided throughout. Fourier Vision will be of value to researchers in image processing & computer vision and, especially, to those who have to deal with superimposed transparent or translucent objects. Researchers in application areas such as medical imaging and acoustic signal processing will also find this of interest.

Statistical Processing Techniques for Noisy Images presents a statistical framework to design algorithms for target detection, tracking, segmentation and classification (identification). Its main goal is to provide the reader with efficient tools for developing algorithms that solve his/her own image processing applications. In particular, such topics as hypothesis test-based detection, fast active contour segmentation and algorithm design for non-conventional imaging systems are comprehensively treated, from theoretical foundations to practical implementations. With a large number of illustrations and practical examples, this book serves as an excellent textbook or reference book for senior or graduate level courses on statistical signal/image processing, as well as a reference for researchers in related fields.

Morphometrics is concerned with the study of variations and change in the form (size and shape) of organisms or objects adding a quantitative element to descriptions and thereby facilitating the comparison of different objects and organisms. This volume provides an introduction to morphometrics in a clear and simple way without recourse to complex mathematics and statistics. This introduction is followed by a series of case studies describing the variety of applications of morphometrics from paleontology and evolutionary ecology to archaeological artifacts analysis. This is followed by a presentation of future applications of morphometrics and state of the art software for analyzing and comparing shape.

This book constitutes the proceedings of the 10th German Conference on Multiagent System Technologies held in Trier Germany, in October 2012. The 7 revised full papers presented together with 6 short parers and one invited paper were carefully reviewed and selected from 39 submissions. The paper cover various research topics in intelligent agents and multi-agent-systems. In particular, the conference investigated technologies for truly open distributed systems covering a wide spectrum of approaches from self-organization and autonomous systems to agreement computing.

This book constitutes the refereed proceedings of the Third Workshop on Human Behavior Understanding, HBU 2012, held in Vilamoura, Portugal, in October 2012. The 14 revised papers presented were carefully reviewed and selected from 31 submissions. The papers are organized in topical sections on sensing human behavior; social and affective signals; human-robot interaction; imitation and learning from demonstration.

An Analog VLSI System for Stereoscopic Vision investigates the interaction of the physical medium and the computation in both biological and analog VLSI systems by synthesizing a functional neuromorphic system in silicon. In both the synthesis and analysis of the system, a point of view from within the system is adopted rather than that of an omniscient designer drawing a blueprint. This perspective projects the design and the designer into a living landscape. The motivation for a machine-centered perspective is explained in the first chapter. The second chapter describes the evolution of the silicon retina. The retina accurately encodes visual information over orders of magnitude of ambient illumination, using mismatched components that are calibrated as part of the encoding process. The visual abstraction created by the retina is suitable for transmission through a limited bandwidth channel. The third chapter introduces a general method for interchip communication, the address-event representation, which is used for transmission of retinal data. The address-event representation takes advantage of the speed of CMOS relative to biological neurons to preserve the information of biological action potentials using digital circuitry in place of axons. The fourth chapter describes a collective circuit that computes stereodisparity. In this circuit, the processing that corrects for imperfections in the hardware compensates for inherent ambiguity in the environment. The fifth chapter demonstrates a primitive working stereovision system. An Analog VLSI System for Stereoscopic Vision contributes to both computer engineering and neuroscience at a concrete level. Through the construction of a working analog of biological vision subsystems, new circuits for building brain-style analog computers have been developed. Specific neuropysiological and psychophysical results in terms of underlying electronic mechanisms are explained. These examples demonstrate the utility of using biological principles for building brain-style computers and the significance of building brain-style computers for understanding the nervous system.

This book constitutes the thoroughly reviewed post-proceedings of the 8th International Workshop on Argumentation in Multi-Agent Systems, ArgMas 2011, held in Taipei, Taiwan in May 2011 in association with the 10th International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS 2011). The 8 revised full papers taken from ArgMAS 2011. Also included are 5 invited papers based on presentations on argumentation at the AAMAS 2011 main conference. All together the 13 papers included in the book give a representative overview on current research on argumentation in multi-agent systems. The papers are listed alphabetically by first author within three thematic topics: foundations and theory; argumentation and dialogue; and applications.

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 shape, 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.

Human Face Recognition Using Third-Order Synthetic Neural Networks explores the viability of the application of High-order synthetic neural network technology to transformation-invariant recognition of complex visual patterns. High-order networks require little training data (hence, short training times) and have been used to perform transformation-invariant recognition of relatively simple visual patterns, achieving very high recognition rates. The successful results of these methods provided inspiration to address more practical problems which have grayscale as opposed to binary patterns (e.g., alphanumeric characters, aircraft silhouettes) and are also more complex in nature as opposed to purely edge-extracted images - human face recognition is such a problem. Human Face Recognition Using Third-Order Synthetic Neural Networks serves as an excellent reference for researchers and professionals working on applying neural network technology to the recognition of complex visual patterns.

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.

Measurement of Image Velocity presents a computational framework for computing motion information from sequences of images. Its specific goal is the measurement of image velocity (or optical flow), the projection of 3-D object motion onto the 2-D image plane. The formulation of the problem emphasizes the geometric and photometric properties of image formation, and the occurrence of multiple image velocities caused, for example, by specular reflections, shadows, or transparency. The method proposed for measuring image velocity is based on the phase behavior in the output of velocity-tuned filters. Extensive experimental work is used to show that phase can be a reliable source of pure image translation, small geometric deformation, smooth contrast variations, and multiple local velocities. Extensive theorectical analysis is used to explain the robustness of phase with respect to deviations from image translation, and to detect situations in which phase becomes unstable. The results indicate that optical flow may be extracted reliably for computing egomotion and structure from motion. The monograph also contains a review of other techniques and frequency analysis applied to image sequences, and it discusses the closely related topics of zero-crossing tracking, gradient-based methods, and the measurement of binocular disparity. The work is relevant to those studying machine vision and visual perception.

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 conference proceedings of the 9th International Conference on Advances in Computer Entertainment, ACE 2012, held in Kathmandu, Nepal, in November 2012. The 10 full paper and 19 short papers presented together with 5 papers from the special track Arts and Culture and 35 extended abstracts were carefully reviewed and selected from a total of 140 submissions in all categories. The papers cover topics across a wide spectrum of disciplines including computer science, design, arts, sociology, anthropology, psychology, and marketing. Focusing on all areas related to interactive entertainment they aim at stimulating discussion in the development of new and compelling entertainment computing and interactive art concepts and applications.