Advances in Computer Vision and Pattern Recognition - Böcker

The problem of structure and motion recovery from image sequences is an important theme in computer vision. Considerable progress has been made in this field during the past two decades, resulting in successful applications in robot navigation, augmented reality, industrial inspection, medical image analysis, and digital entertainment, among other areas. However, many of these methods work only for rigid objects and static scenes. The study of non-rigid structure from motion is not only of academic significance, but also has important practical applications in real-world, nonrigid or dynamic scenarios, such as human facial expressions and moving vehicles.This practical guide/reference provides a comprehensive overview of Euclidean structure and motion recovery, with a specific focus on factorization-based algorithms. The book discusses the latest research in this field, including the extension of the factorization algorithm to recover the structure of non-rigid objects, and presents some new algorithms developed by the authors. Readers require no significant knowledge of computer vision, although some background on projective geometry and matrix computation would be beneficial.Topics and features: presents the first systematic study of structure and motion recovery of both rigid and non-rigid objects from images sequences; discusses in depth the theory, techniques, and applications of rigid and non-rigid factorization methods in three dimensional computer vision; examines numerous factorization algorithms, covering affine, perspective and quasi-perspective projection models; provides appendices describing the mathematical principles behind projective geometry, matrix decomposition, least squares, and nonlinear estimation techniques; includes chapter-ending review questions, and a glossary of terms used in the book.This unique text offers practical guidance in real applications and implementations of 3D modeling systems for practitioners incomputer vision and pattern recognition, as well as serving as an invaluable source of new algorithms and methodologies for structure and motion recovery for graduate students and researchers.

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.

Most biometric systems employed for human recognition require physical contact with, or close proximity to, a cooperative subject. Far more challenging is the ability to reliably recognize individuals at a distance, when viewed from an arbitrary angle under real-world environmental conditions. Gait and face data are the two biometrics that can be most easily captured from a distance using a video camera.This comprehensive and logically organized text/reference addresses the fundamental problems associated with gait and face-based human recognition, from color and infrared video data that are acquired from a distance. It examines both model-free and model-based approaches to gait-based human recognition, including newly developed techniques where the both the model and the data (obtained from multiple cameras) are in 3D. In addition, the work considers new video-based techniques for face profile recognition, and for the super-resolution of facial imagery obtained at different angles. Finally, the book investigates integrated systems that detect and fuse both gait and face biometrics from video data. Topics and features: discusses a framework for human gait analysis based on Gait Energy Image, a spatio-temporal gait representation; evaluates the discriminating power of model-based gait features using Bayesian statistical analysis; examines methods for human recognition using 3D gait biometrics, and for moving-human detection using both color and thermal image sequences; describes approaches for the integration face profile and gait biometrics, and for super-resolution of frontal and side-view face images; introduces an objective non-reference quality evaluation algorithm for super-resolved images; presents performance comparisons between different biometrics and different fusion methods for integrating gait and super-resolved face from video.This unique and authoritative text is an invaluable resource for researchers and graduate students ofcomputer vision, pattern recognition and biometrics. The book will also be of great interest to professional engineers of biometric systems.

This text reviews the issues involved in handling and processing digital documents. Examining the full range of a document’s lifetime, the book covers acquisition, representation, security, pre-processing, layout analysis, understanding, analysis of single components, information extraction, filing, indexing and retrieval. Features: provides a list of acronyms and a glossary of technical terms; contains appendices covering key concepts in machine learning, and providing a case study on building an intelligent system for digital document and library management; discusses issues of security, and legal aspects of digital documents; examines core issues of document image analysis, and image processing techniques of particular relevance to digitized documents; reviews the resources available for natural language processing, in addition to techniques of linguistic analysis for content handling; investigates methods for extracting and retrieving data/information from a document.

This unique text/reference discusses in depth the two integral components of reconstructive surgery; fracture detection, and reconstruction from broken bone fragments. In addition to supporting its application-oriented viewpoint with detailed coverage of theoretical issues, the work incorporates useful algorithms and relevant concepts from both graph theory and statistics. Topics and features: presents practical solutions for virtual craniofacial reconstruction and computer-aided fracture detection; discusses issues of image registration, object reconstruction, combinatorial pattern matching, and detection of salient points and regions in an image; investigates the concepts of maximum-weight graph matching, maximum-cardinality minimum-weight matching for a bipartite graph, determination of minimum cut in a flow network, and construction of automorphs of a cycle graph; examines the techniques of Markov random fields, hierarchical Bayesian restoration, Gibbs sampling, and Bayesian inference.

This book presents a comprehensive review of image processing methods, for the analysis of land use in residential areas. Combining a theoretical framework with highly practical applications, the book describes a system for the effective detection of single houses and streets in very high resolution. Topics and features: with a Foreword by Prof. Dr. Peter Reinartz of the German Aerospace Center; provides end-of-chapter summaries and review questions; presents a detailed review on remote sensing satellites; examines the multispectral information that can be obtained from satellite images, with a focus on vegetation and shadow-water indices; investigates methods for land-use classification, introducing precise graph theoretical measures over panchromatic images; addresses the problem of detecting residential regions; describes a house and street network-detection subsystem; concludes with a summary of the key ideas covered in the book.

Medical imaging is an important topic which is generally recognised as key to better 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 state-of-the-art model-based segmentation techniques which are applied to cardiac, brain, breast and microscopic cancer cell imaging. It includes contributions from authors based in both industry and academia and presents a host of new material including algorithms for:- brain segmentation applied to MR;- neuro-application using MR; - parametric and geometric deformable models for brain segmentation;- left ventricle segmentation and analysis using least squares and constrained least squares models for cardiac X-rays; - left ventricle analysis in echocardioangiograms;- breast lesion detection in digital mammograms;detection of cells in cell images.As an overview of the latest techniques, this book will be of particular interest to students and researchers in medical engineering, image processing, computer graphics, mathematical modelling and data analysis. It will also be of interest to researchers in the fields of mammography, cardiology, pathology and neurology.

Automatic (machine) recognition, description, classification, and groupings of patterns are important problems in a variety of engineering and scientific disciplines such as biology, psychology, medicine, marketing, computer vision, artificial intelligence, and remote sensing. Given a pattern, its recognition/classification may consist of one of the following two tasks: (1) supervised classification (also called discriminant analysis); the input pattern is assigned to one of several predefined classes, (2) unsupervised classification (also called clustering); no pattern classes are defined a priori and patterns are grouped into clusters based on their similarity. Interest in the area of pattern recognition has been renewed recently due to emerging applications which are not only challenging but also computationally more demanding (e. g. , bioinformatics, data mining, document classification, and multimedia database retrieval). Among the various frameworks in which pattern recognition has been traditionally formulated, the statistical approach has been most intensively studied and used in practice. More recently, neural network techniques and methods imported from statistical learning theory have received increased attention. Neural networks and statistical pattern recognition are two closely related disciplines which share several common research issues. Neural networks have not only provided a variety of novel or supplementary approaches for pattern recognition tasks, but have also offered architectures on which many well-known statistical pattern recognition algorithms can be mapped for efficient (hardware) implementation. On the other hand, neural networks can derive benefit from some well-known results in statistical pattern recognition.

This important text/reference presents state-of-the-art research on intelligent vehicles, covering not only topics of object/obstacle detection and recognition, but also aspects of vehicle motion control. With an emphasis on both high-level concepts, and practical detail, the text links theory, algorithms, and issues of hardware and software implementation in intelligent vehicle research. Topics and features: presents a thorough introduction to the development and latest progress in intelligent vehicle research, and proposes a basic framework; provides detection and tracking algorithms for structured and unstructured roads, as well as on-road vehicle detection and tracking algorithms using boosted Gabor features; discusses an approach for multiple sensor-based multiple-object tracking, in addition to an integrated DGPS/IMU positioning approach; examines a vehicle navigation approach using global views; introduces algorithms for lateral and longitudinal vehicle motion control.

This book presents a thorough and detailed guide to image registration, outlining the principles and reviewing state-of-the-art tools and methods. The book begins by identifying the components of a general image registration system, and then describes the design of each component using various image analysis tools. The text reviews a vast array of tools and methods, not only describing the principles behind each tool and method, but also measuring and comparing their performances using synthetic and real data. Features: discusses similarity/dissimilarity measures, point detectors, feature extraction/selection and homogeneous/heterogeneous descriptors; examines robust estimators, point pattern matching algorithms, transformation functions, and image resampling and blending; covers principal axes methods, hierarchical methods, optimization-based methods, edge-based methods, model-based methods, and adaptive methods; includes a glossary, an extensive list of references, and an appendix on PCA.

Theoriginalmotivationsfordevelopingopticalcharacterrecognitiontechnologies weremodesttoconvertprintedtexton?atphysicalmediatodigitalform,prod- ingmachine-readabledigitalcontent. Bydoingthis,wordsthathadbeeninertand bound to physical material would be brought into the digital realm and thus gain newandpowerfulfunctionalitiesandanalyticalpossibilities. First-generation digital OCR researchers in the 1970s quickly realized that by limiting their ambitions primarily to contemporary documents printed in st- dard font type from the modern Roman alphabet (and of these, mostly English language materials), they were constraining the possibilities for future research andtechnologiesconsiderably. Domainresearchersalsosawthatthetrajectoryof OCR technologies if left unchanged would exclude a large portion of the human record. Digitalconversionofdocumentsandmanuscriptsinotheralphabets,scripts, and cursive styles was of critical importance.Embedded in non-Roman alp- bet source documents, including ancient manuscripts, papyri scrolls, clay tablets, and other inscribed artifacts was not only a wealth of scholarly information but alsonewopportunitiesandchallengesforadvancingOCR,imagingsciences,and othercomputationalresearchareas. Thelimitingcircumstancesatthetimeincluded the rudimentary capability (and high cost) of computational resources and lack of network-accessible digital content. Since then computational technology has advancedataveryrapidpaceandnetworkinginfrastructurehasproliferated. Over time, thisexponential decrease inthecost of computation, memory, and com- nicationsbandwidthcombinedwiththeexponentialincreaseinInternet-accessible digitalcontenthastransformededucation,scholarship,andresearch. Largenumbers ofresearchers,scholars,andstudentsuseanddependuponInternet-basedcontent andcomputationalresources. Thechaptersinthisbookdescribeacriticallyimportantareaofinvestigation- addressingconversionofIndicscriptintomachine-readableform. Roughestimates haveitthatcurrentlymorethanabillionpeopleuseIndicscripts. Collectively,Indic historic and cultural documents contain a vast richness of human knowledge and experience.The state-of-the-art research described in this book demonstrates the multiple values associated with these activities. Technically, the problems associated with Indicscriptrecognitionareverydif?cultandwillcontributetoandinformrelated v vi Foreword scriptrecognitionefforts. Theworkalsohasenormousconsequenceforenriching andenablingthestudyofIndicculturalheritagematerialsandthehistoricrecord of its people. This in turn broadens the intellectual context for domain scholars focusingonothersocieties,ancientandmodern. Digital character recognition has brought about another milestone in coll- tivecommunicationbybringinginert,?xed-in-place,textintoaninteractivedi- talrealm. Indoingso,theinformationhasgainedadditionalfunctionalitieswhich expandourabilitiestoconnect,combine,contextualize,share,andcollaboratively pursue knowledge making. High-quality Internet content continues to grow in an explosivefashion. Inthenewglobalcyberenvironment,thefunctionalitiesandapp- cationsofdigitalinformationcontinuetotransformknowledgeintonewundersta- ingsofhumanexperienceandtheworldinwhichwelive.Thepossibilitiesforthe futurearelimitedonlybyavailableresearchresourcesandcapabilitiesandtheim- inationandcreativityofthosewhousethem. Arlington,Virginia StephenM.

This revised and updated text presents the computational and mathematical procedures underlying data collection, image reconstruction, and image display in computerized tomography. New topics: the fast calculation of a ray sum for a digitized picture, the task-oriented comparison of reconstruction algorithm performance, blob basis functions and the linogram method for image reconstruction. Features: Describes how projection data are obtained and the resulting reconstructions are used; Presents a comparative evaluation of reconstruction methods; Investigates reconstruction algorithms; Explores basis functions, functions to be optimized, norms, generalized inverses, least squares solutions, maximum entropy solutions, and most likely estimates; Discusses SNARK09, a large programming system for image reconstruction; Concludes each chapter with helpful Notes and References sections. An excellent guide for practitioners, it can also serve as a textbook for an introductory graduate course.

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.

Rapid development of computer hardware has enabled usage of automatic object recognition in an increasing number of applications, ranging from industrial image processing to medical applications, as well as tasks triggered by the widespread use of the internet. Each area of application has its specific requirements, and consequently these cannot all be tackled appropriately by a single, general-purpose algorithm.This easy-to-read text/reference provides a comprehensive introduction to the field of object recognition (OR). The book presents an overview of the diverse applications for OR and highlights important algorithm classes, presenting representative example algorithms for each class. The presentation of each algorithm describes the basic algorithm flow in detail, complete with graphical illustrations. Pseudocode implementations are also included for many of the methods, and definitions are supplied for terms which may be unfamiliar to the novice reader. Supporting a clear and intuitive tutorial style, the usage of mathematics is kept to a minimum.Topics and features: presents example algorithms covering global approaches, transformation-search-based methods, geometrical model driven methods, 3D object recognition schemes, flexible contour fitting algorithms, and descriptor-based methods; explores each method in its entirety, rather than focusing on individual steps in isolation, with a detailed description of the flow of each algorithm, including graphical illustrations; explains the important concepts at length in a simple-to-understand style, with a minimum usage of mathematics; discusses a broad spectrum of applications, including some examples from commercial products; contains appendices discussing topics related to OR and widely used in the algorithms, (but not at the core of the methods described in the chapters).Practitioners of industrial image processing will find this simple introduction and overview to OR a valuable reference, as will graduate students in computer vision courses.Marco Treiber is a software developer at Siemens Electronics Assembly Systems, Munich, Germany, where he is Technical Lead in Image Processing for the Vision System of SiPlace placement machines, used in SMT assembly.

The problem of structure and motion recovery from image sequences is an important theme in computer vision. Considerable progress has been made in this field during the past two decades, resulting in successful applications in robot navigation, augmented reality, industrial inspection, medical image analysis, and digital entertainment, among other areas. However, many of these methods work only for rigid objects and static scenes. The study of non-rigid structure from motion is not only of academic significance, but also has important practical applications in real-world, nonrigid or dynamic scenarios, such as human facial expressions and moving vehicles.This practical guide/reference provides a comprehensive overview of Euclidean structure and motion recovery, with a specific focus on factorization-based algorithms. The book discusses the latest research in this field, including the extension of the factorization algorithm to recover the structure of non-rigid objects, and presents some new algorithms developed by the authors. Readers require no significant knowledge of computer vision, although some background on projective geometry and matrix computation would be beneficial.Topics and features: presents the first systematic study of structure and motion recovery of both rigid and non-rigid objects from images sequences; discusses in depth the theory, techniques, and applications of rigid and non-rigid factorization methods in three dimensional computer vision; examines numerous factorization algorithms, covering affine, perspective and quasi-perspective projection models; provides appendices describing the mathematical principles behind projective geometry, matrix decomposition, least squares, and nonlinear estimation techniques; includes chapter-ending review questions, and a glossary of terms used in the book.This unique text offers practical guidance in real applications and implementations of 3D modeling systems for practitioners incomputer vision and pattern recognition, as well as serving as an invaluable source of new algorithms and methodologies for structure and motion recovery for graduate students and researchers.

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 practitionersfrom 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.

Most biometric systems employed for human recognition require physical contact with, or close proximity to, a cooperative subject. Far more challenging is the ability to reliably recognize individuals at a distance, when viewed from an arbitrary angle under real-world environmental conditions. Gait and face data are the two biometrics that can be most easily captured from a distance using a video camera.This comprehensive and logically organized text/reference addresses the fundamental problems associated with gait and face-based human recognition, from color and infrared video data that are acquired from a distance. It examines both model-free and model-based approaches to gait-based human recognition, including newly developed techniques where the both the model and the data (obtained from multiple cameras) are in 3D. In addition, the work considers new video-based techniques for face profile recognition, and for the super-resolution of facial imagery obtained at different angles. Finally, the book investigates integrated systems that detect and fuse both gait and face biometrics from video data. Topics and features: discusses a framework for human gait analysis based on Gait Energy Image, a spatio-temporal gait representation; evaluates the discriminating power of model-based gait features using Bayesian statistical analysis; examines methods for human recognition using 3D gait biometrics, and for moving-human detection using both color and thermal image sequences; describes approaches for the integration face profile and gait biometrics, and for super-resolution of frontal and side-view face images; introduces an objective non-reference quality evaluation algorithm for super-resolved images; presents performance comparisons between different biometrics and different fusion methods for integrating gait and super-resolved face from video.This unique and authoritative text is an invaluable resource for researchers and graduate students ofcomputer vision, pattern recognition and biometrics. The book will also be of great interest to professional engineers of biometric systems.

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.

This text reviews the issues involved in handling and processing digital documents. Examining the full range of a document’s lifetime, the book covers acquisition, representation, security, pre-processing, layout analysis, understanding, analysis of single components, information extraction, filing, indexing and retrieval. Features: provides a list of acronyms and a glossary of technical terms; contains appendices covering key concepts in machine learning, and providing a case study on building an intelligent system for digital document and library management; discusses issues of security, and legal aspects of digital documents; examines core issues of document image analysis, and image processing techniques of particular relevance to digitized documents; reviews the resources available for natural language processing, in addition to techniques of linguistic analysis for content handling; investigates methods for extracting and retrieving data/information from a document.

This unique text/reference discusses in depth the two integral components of reconstructive surgery; fracture detection, and reconstruction from broken bone fragments. In addition to supporting its application-oriented viewpoint with detailed coverage of theoretical issues, the work incorporates useful algorithms and relevant concepts from both graph theory and statistics. Topics and features: presents practical solutions for virtual craniofacial reconstruction and computer-aided fracture detection; discusses issues of image registration, object reconstruction, combinatorial pattern matching, and detection of salient points and regions in an image; investigates the concepts of maximum-weight graph matching, maximum-cardinality minimum-weight matching for a bipartite graph, determination of minimum cut in a flow network, and construction of automorphs of a cycle graph; examines the techniques of Markov random fields, hierarchical Bayesian restoration, Gibbs sampling, and Bayesian inference.

This book presents a comprehensive review of image processing methods, for the analysis of land use in residential areas. Combining a theoretical framework with highly practical applications, the book describes a system for the effective detection of single houses and streets in very high resolution. Topics and features: with a Foreword by Prof. Dr. Peter Reinartz of the German Aerospace Center; provides end-of-chapter summaries and review questions; presents a detailed review on remote sensing satellites; examines the multispectral information that can be obtained from satellite images, with a focus on vegetation and shadow-water indices; investigates methods for land-use classification, introducing precise graph theoretical measures over panchromatic images; addresses the problem of detecting residential regions; describes a house and street network-detection subsystem; concludes with a summary of the key ideas covered in the book.

The development of technologies for the identi?cation of individuals has driven the interest and curiosity of many people. Spearheaded and inspired by the Bertillon coding system for the classi?cation of humans based on physical measurements, scientists and engineers have been trying to invent new devices and classi?cation systems to capture the human identity from its body measurements. One of the main limitations of the precursors of today’s biometrics, which is still present in the vast majority of the existing biometric systems, has been the need to keep the device in close contact with the subject to capture the biometric measurements. This clearly limits the applicability and convenience of biometric systems. This book presents an important step in addressing this limitation by describing a number of methodologies to capture meaningful biometric information from a distance. Most materials covered in this book have been presented at the International Summer School on Biometrics which is held every year in Alghero, Italy and which has become a ?agship activity of the IAPR Technical Committee on Biometrics (IAPR TC4). The last four chapters of the book are derived from some of the best p- sentations by the participating students of the school. The educational value of this book is also highlighted by the number of proposed exercises and questions which will help the reader to better understand the proposed topics.

Why are We Writing This Book? Visual data (graphical, image, video, and visualized data) affect every aspect of modern society. The cheap collection, storage, and transmission of vast amounts of visual data have revolutionized the practice of science, technology, and business. Innovations from various disciplines have been developed and applied to the task of designing intelligent machines that can automatically detect and exploit useful regularities (patterns) in visual data. One such approach to machine intelligence is statistical learning and pattern analysis for visual data. Over the past two decades, rapid advances have been made throughout the ?eld of visual pattern analysis. Some fundamental problems, including perceptual gro- ing,imagesegmentation, stereomatching, objectdetectionandrecognition,and- tion analysis and visual tracking, have become hot research topics and test beds in multiple areas of specialization, including mathematics, neuron-biometry, and c- nition. A great diversity of models and algorithms stemming from these disciplines has been proposed. To address the issues of ill-posed problems and uncertainties in visual pattern modeling and computing, researchers have developed rich toolkits based on pattern analysis theory, harmonic analysis and partial differential eq- tions, geometry and group theory, graph matching, and graph grammars. Among these technologies involved in intelligent visual information processing, statistical learning and pattern analysis is undoubtedly the most popular and imp- tant approach, and it is also one of the most rapidly developing ?elds, with many achievements in recent years. Above all, it provides a unifying theoretical fra- work for intelligent visual information processing applications.

Automatie object recognition is a multidisciplinary research area using con­ cepts and tools from mathematics, computing, optics, psychology, pattern recognition, artificial intelligence and various other disciplines. The purpose of this research is to provide a set of coherent paradigms and algorithms for the purpose of designing systems that will ultimately emulate the functions performed by the Human Visual System (HVS). Hence, such systems should have the ability to recognise objects in two or three dimensions independently of their positions, orientations or scales in the image. The HVS is employed for tens of thousands of recognition events each day, ranging from navigation (through the recognition of landmarks or signs), right through to communication (through the recognition of characters or people themselves). Hence, the motivations behind the construction of recognition systems, which have the ability to function in the real world, is unquestionable and would serve industrial (e.g. quality control), military (e.g. automatie target recognition) and community needs (e.g. aiding the visually impaired). Scope, Content and Organisation of this Book This book provides a comprehensive, yet readable foundation to the field of object recognition from which research may be initiated or guided. It repre­ sents the culmination of research topics that I have either covered personally or in conjunction with my PhD students. These areas include image acqui­ sition, 3-D object reconstruction, object modelling, and the matching of ob­ jects, all of which are essential in the construction of an object recognition system.

The potential of consumer depth cameras extends well beyond entertainment and gaming, to real-world commercial applications. This authoritative text reviews the scope and impact of this rapidly growing field, describing the most promising Kinect-based research activities, discussing significant current challenges, and showcasing exciting applications. Features: presents contributions from an international selection of preeminent authorities in their fields, from both academic and corporate research; addresses the classic problem of multi-view geometry of how to correlate images from different viewpoints to simultaneously estimate camera poses and world points; examines human pose estimation using video-rate depth images for gaming, motion capture, 3D human body scans, and hand pose recognition for sign language parsing; provides a review of approaches to various recognition problems, including category and instance learning of objects, and human activity recognition; with a Foreword by Dr. Jamie Shotton.

This book presents a detailed analysis of spectral imaging, describing how it can be used for the purposes of material identification, object recognition and scene understanding. The opportunities and challenges of combining spatial and spectral information are explored in depth, as are a wide range of applications. Features: discusses spectral image acquisition by hyperspectral cameras, and the process of spectral image formation; examines models of surface reflectance, the recovery of photometric invariants, and the estimation of the illuminant power spectrum from spectral imagery; describes spectrum representations for the interpolation of reflectance and radiance values, and the classification of spectra; reviews the use of imaging spectroscopy for material identification; explores the recovery of reflection geometry from image reflectance; investigates spectro-polarimetric imagery, and the recovery of object shape and material properties using polarimetric images captured froma single view.

This book surveys the state of the art in multidimensional, physically-correct visual texture modeling. Features: reviews the entire process of texture synthesis, including material appearance representation, measurement, analysis, compression, modeling, editing, visualization, and perceptual evaluation; explains the derivation of the most common representations of visual texture, discussing their properties, advantages, and limitations; describes a range of techniques for the measurement of visual texture, including BRDF, SVBRDF, BTF and BSSRDF; investigates the visualization of textural information, from texture mapping and mip-mapping to illumination- and view-dependent data interpolation; examines techniques for perceptual validation and analysis, covering both standard pixel-wise similarity measures and also methods of visual psychophysics; reviews the applications of visual textures, from visual scene analysis in medical applications, to high-quality visualizations in the automotive industry.

This practical and easy-to-follow text explores the theoretical underpinnings of decision forests, organizing the vast existing literature on the field within a new, general-purpose forest model. Topics and features: with a foreword by Prof. Y. Amit and Prof. D. Geman, recounting their participation in the development of decision forests; introduces a flexible decision forest model, capable of addressing a large and diverse set of image and video analysis tasks; investigates both the theoretical foundations and the practical implementation of decision forests; discusses the use of decision forests for such tasks as classification, regression, density estimation, manifold learning, active learning and semi-supervised classification; includes exercises and experiments throughout the text, with solutions, slides, demo videos and other supplementary material provided at an associated website; provides a free, user-friendly software library, enabling the reader to experiment with forests ina hands-on manner.

This unique text/reference describes in detail the latest advances in unsupervised process monitoring and fault diagnosis with machine learning methods. Abundant case studies throughout the text demonstrate the efficacy of each method in real-world settings. The broad coverage examines such cutting-edge topics as the use of information theory to enhance unsupervised learning in tree-based methods, the extension of kernel methods to multiple kernel learning for feature extraction from data, and the incremental training of multilayer perceptrons to construct deep architectures for enhanced data projections. Topics and features: discusses machine learning frameworks based on artificial neural networks, statistical learning theory and kernel-based methods, and tree-based methods; examines the application of machine learning to steady state and dynamic operations, with a focus on unsupervised learning; describes the use of spectral methods in process fault diagnosis.