Bir Bhanu - Böcker

Evolutionary computation is becoming increasingly important for computer vision and pattern recognition and provides a systematic way of synthesis and analysis of object detection and recognition systems. Incorporating "learning" into recognition systems will enable these systems to automatically generate new features on the fly and cleverly select a good subset of features according to the type of objects and images to which they are applied. This unique monograph investigates evolutionary computational techniques--such as genetic programming, linear genetic programming, coevolutionary genetic programming and genetic algorithms--to automate the synthesis and analysis of object detection and recognition systems. The purpose of incorporating learning into the system design is to avoid the time-consuming process of feature generation and selection and to reduce the cost of building object detection and recognition systems.Researchers, professionals, engineers, and students working in computer vision, pattern recognition, target recognition, machine learning, evolutionary learning, image processing, knowledge discovery and data mining, cybernetics, robotics, automation and psychology will find this well-developed and organized volume an invaluable resource.

Computer vision (CV) research seeks to provide computers with human-like perception capabilities so that they can sense the environment, understand the sensed data, take appropriate actions, and learn from this experience in order to enhance future performance. The field has evolved from early pattern recognition and image processing to advanced image understanding, including model-based and knowledge-based vision. This book shows how machine learning can help create robust, flexible vision techniques for optimal functioning in real-world scenarios.

In today's security-conscious society, real-world applications for authentication or identification require a highly accurate system for recognizing individual humans. The required level of performance cannot be achieved through the use of a single biometric such as face, fingerprint, ear, iris, palm, gait or speech. Fusing multiple biometrics enables the indexing of large databases, more robust performance and enhanced coverage of populations. Multiple biometrics are also naturally more robust against attacks than single biometrics. This book addresses a broad spectrum of research issues on multibiometrics for human identification, ranging from sensing modes and modalities to fusion of biometric samples and combination of algorithms. It covers publicly available multibiometrics databases, theoretical and empirical studies on sensor fusion techniques in the context of biometrics authentication, identification and performance evaluation and prediction.

Mobile robots operating in real-world, outdoor scenarios depend on dynamic scene understanding for detecting and avoiding obstacles, recognizing landmarks, acquiring models and for detecting and tracking moving objects. Motion understanding has been an active research effort for more than a decade, searching for solutions to some of these problems; however, it still remains one of the more difficult and challenging areas of computer vision research. "Qualitative Motion Understanding" describes a qualitative approach to dynamic scene and motion analysis, called DRIVE (Dynamic Reasoning from Integrated Visual Evidence). The DRIVE system addresses the problems of estimating the robot's egomotion, reconstructing the observed 3-D scene structure, and evaluating the motion of individual objects from a sequence of monocular images. The approach is based on the FOE (focus on expansion) concept, but it takes a somewhat unconventional route. The DRIVE system uses a qualitative scene model and a fuzzy focus of expansion to estimate robot motion from visual clues, to detect and track moving objects, and to construct and maintain a global dynamic reference model.

Image segmentation is generally the first task in any automated image understanding application, such as autonomous vehicle navigation, object recognition, photointerpretation, etc. All subsequent tasks, such as feature extraction, object detection, and object recognition, rely heavily on the quality of segmentation. One of the fundamental weaknesses of current image segmentation algorithms is their inability to adapt the segmentation process as real-world changes are reflected in the image. Only after numerous modifications to an algorithm's control parameters can any current image segmentation technique be used to handle the diversity of images encountered in real-world applications. "Genetic Learning for Adaptive Image Segmentation" presents the first closed-loop image segmentation system that incorporates genetic and other algorithms to adapt the segmentation process to changes in image characteristics caused by variable environmental conditions, such as time of day, time of year, weather, etc. Image segmentation performance is evaluated using multiple measures of segmentation quality.These quality measures include global characteristics of the entire image as well as local features of individual object regions in the image. This adaptive image segmentation system provides continuous adaptation to normal environmental variations, exhibits learning capabilities, and provides robust performance when interacting with a dynamic environment. This research is directed towards adapting the performance of a well-known existing segmentation algorithm (Phoenix) across a wide variety of environmental conditions which cause changes in the image characteristics. The book presents a number of experimental results and compares performance with standard techniques used in computer vision for both consistency and quality of segmentation results. These results demonstrate: (a) the ability to adapt the segmentation performance in both indoor and outdoor colour imagery; and (b) that learning from experience can be used to improve the segmentation performance over time.

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.

Large-scale video networks are of increasing importance in a wide range of applications. However, the development of automated techniques for aggregating and interpreting information from multiple video streams in real-life scenarios is a challenging area of research.Collecting the work of leading researchers from a broad range of disciplines, this timely text/reference offers an in-depth survey of the state of the art in distributed camera networks. The book addresses a broad spectrum of critical issues in this highly interdisciplinary field: current challenges and future directions; video processing and video understanding; simulation, graphics, cognition and video networks; wireless video sensor networks, communications and control; embedded cameras and real-time video analysis; applications of distributed video networks; and educational opportunities and curriculum-development.Topics and features: presents an overview of research in areas of motion analysis, invariants, multiple cameras for detection, object tracking and recognition, and activities in video networks; provides real-world applications of distributed video networks, including force protection, wide area activities, port security, and recognition in night-time environments; describes the challenges in graphics and simulation, covering virtual vision, network security, human activities, cognitive architecture, and displays; examines issues of multimedia networks, registration, control of cameras (in simulations and real networks), localization and bounds on tracking; discusses system aspects of video networks, with chapters on providing testbed environments, data collection on activities, new integrated sensors for airborne sensors, face recognition, and building sentient spaces; investigates educational opportunities and curriculum development from the perspective of computer science and electrical engineering.This unique text will be of great interest to researchers and graduate students of computer vision and pattern recognition, computer graphics and simulation, image processing and embedded systems, and communications, networks and controls. The large number of example applications will also appeal to application engineers.

Biometrics such as fingerprint, face, gait, iris, voice and signature, recognizes one's identity using his/her physiological or behavioural characteristics. Among these biometric signs, fingerprint has been researched the longest period of time, and shows the most promising future in real-world applications. However, because of the complex distortions among the different impressions of the same finger, fingerprint recognition is still a challenging problem. "Computational Algorithms For Fingerprint Recognition" presents an entire range of novel computational algorithms for fingerprint recognition. These include feature extraction, indexing, matching, classification and performance prediction/validation methods, which have been compared with state-of-art algorithms and found to be effective and efficient on real-world data. All the algorithms have been evaluated on NIST-4 database from National Institute of Standards and Technology (NIST).Specific algorithms addressed include: learned template based minutiae extraction algorithm; triplets of minutiae based fingerprint indexing algorithm; genetic algorithm based fingerprint matching algorithm; genetic programming based feature learning algorithm for fingerprint classification; comparison of classification and indexing based approaches for identification; and fundamental fingerprint matching performance prediction analysis and its validation. "Computational Algorithms For Fingerprint Recognition" is designed for a professional audience composed of researchers and practitioners in industry. This book is also suitable as a secondary text for graduate-level students in computer science and engineering.

Evolutionary computation is becoming increasingly important for computer vision and pattern recognition and provides a systematic way of synthesis and analysis of object detection and recognition systems. Incorporating "learning" into recognition systems will enable these systems to automatically generate new features on the fly and cleverly select a good subset of features according to the type of objects and images to which they are applied.This unique monograph investigates evolutionary computational techniques--such as genetic programming, linear genetic programming, coevolutionary genetic programming and genetic algorithms--to automate the synthesis and analysis of object detection and recognition systems.The purpose of incorporating learning into the system design is to avoid the time-consuming process of feature generation and selection and to reduce the cost of building object detection and recognition systems.Researchers, professionals, engineers, and students working in computer vision, pattern recognition, target recognition, machine learning, evolutionary learning, image processing, knowledge discovery and data mining, cybernetics, robotics, automation and psychology will find this well-developed and organized volume an invaluable resource.

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.

Large-scale video networks are of increasing importance in a wide range of applications. However, the development of automated techniques for aggregating and interpreting information from multiple video streams in real-life scenarios is a challenging area of research.Collecting the work of leading researchers from a broad range of disciplines, this timely text/reference offers an in-depth survey of the state of the art in distributed camera networks. The book addresses a broad spectrum of critical issues in this highly interdisciplinary field: current challenges and future directions; video processing and video understanding; simulation, graphics, cognition and video networks; wireless video sensor networks, communications and control; embedded cameras and real-time video analysis; applications of distributed video networks; and educational opportunities and curriculum-development.Topics and features: presents an overview of research in areas of motion analysis, invariants, multiple cameras for detection, object tracking and recognition, and activities in video networks; provides real-world applications of distributed video networks, including force protection, wide area activities, port security, and recognition in night-time environments; describes the challenges in graphics and simulation, covering virtual vision, network security, human activities, cognitive architecture, and displays; examines issues of multimedia networks, registration, control of cameras (in simulations and real networks), localization and bounds on tracking; discusses system aspects of video networks, with chapters on providing testbed environments, data collection on activities, new integrated sensors for airborne sensors, face recognition, and building sentient spaces; investigates educational opportunities and curriculum development from the perspective of computer science and electrical engineering.This unique text will be of great interest to researchers and graduate students of computer vision and pattern recognition, computer graphics and simulation, image processing and embedded systems, and communications, networks and controls. The large number of example applications will also appeal to application engineers.

Biometrics such as fingerprint, face, gait, iris, voice and signature, recognizes one's identity using his/her physiological or behavioral characteristics. Among these biometric signs, fingerprint has been researched the longest period of time, and shows the most promising future in real-world applications. However, because of the complex distortions among the different impressions of the same finger, fingerprint recognition is still a challenging problem. Computational Algorithms for Fingerprint Recognition presents an entire range of novel computational algorithms for fingerprint recognition. These include feature extraction, indexing, matching, classification, and performance prediction/validation methods, which have been compared with state-of-art algorithms and found to be effective and efficient on real-world data. All the algorithms have been evaluated on NIST-4 database from National Institute of Standards and Technology (NIST). Specific algorithms addressed include:-Learned template based minutiae extraction algorithm, -Triplets of minutiae based fingerprint indexing algorithm, -Genetic algorithm based fingerprint matching algorithm, -Genetic programming based feature learning algorithm for fingerprint classification, -Comparison of classification and indexing based approaches for identification, -Fundamental fingerprint matching performance prediction analysis and its validation.Computational Algorithms for Fingerprint Recognition is designed for a professional audience composed of researchers and practitioners in industry. This book is also suitable as a secondary text for graduate-level students in computer science and engineering.

Image segmentation is generally the first task in any automated image understanding application, such as autonomous vehicle navigation, object recognition, photointerpretation, etc. All subsequent tasks, such as feature extraction, object detection, and object recognition, rely heavily on the quality of segmentation. One of the fundamental weaknesses of current image segmentation algorithms is their inability to adapt the segmentation process as real-world changes are reflected in the image. Only after numerous modifications to an algorithm's control parameters can any current image segmentation technique be used to handle the diversity of images encountered in real-world applications. Genetic Learning for Adaptive Image Segmentation presents the first closed-loop image segmentation system that incorporates genetic and other algorithms to adapt the segmentation process to changes in image characteristics caused by variable environmental conditions, such as time of day, time of year, weather, etc. Image segmentation performance is evaluated using multiple measures of segmentation quality. These quality measures include global characteristics of the entire image as well as local features of individual object regions in the image. This adaptive image segmentation system provides continuous adaptation to normal environmental variations, exhibits learning capabilities, and provides robust performance when interacting with a dynamic environment. This research is directed towards adapting the performance of a well known existing segmentation algorithm (Phoenix) across a wide variety of environmental conditions which cause changes in the image characteristics. The book presents a large number of experimental results and compares performance with standard techniques used in computer vision for both consistency and quality of segmentation results. These results demonstrate, (a) the ability to adapt the segmentation performance in both indoor and outdoor color imagery, and (b) that learning from experience can be used to improve the segmentation performance over time.

Mobile robots operating in real-world, outdoor scenarios depend on dynamic scene understanding for detecting and avoiding obstacles, recognizing landmarks, acquiring models, and for detecting and tracking moving objects. Motion understanding has been an active research effort for more than a decade, searching for solutions to some of these problems; however, it still remains one of the more difficult and challenging areas of computer vision research. Qualitative Motion Understanding describes a qualitative approach to dynamic scene and motion analysis, called DRIVE (Dynamic Reasoning from Integrated Visual Evidence). The DRIVE system addresses the problems of (a) estimating the robot's egomotion, (b) reconstructing the observed 3-D scene structure; and (c) evaluating the motion of individual objects from a sequence of monocular images. The approach is based on the FOE (focus of expansion) concept, but it takes a somewhat unconventional route. The DRIVE system uses a qualitative scene model and a fuzzy focus of expansion to estimate robot motion from visual cues, to detect and track moving objects, and to construct and maintain a global dynamic reference model.

Biometrics deal with recognition of individuals based on their physiological or behavioural characteristics. Researchers have done extensive studies on biometrics such as fingerprint, face, palm print, iris and gait. Ear, a viable new class of biometrics, has certain advantages over face and fingerprint, which are the two most common biometrics in both academic research and industrial applications.This book explores all aspects of 3D ear recognition: representation, detection, recognition, indexing and performance prediction. It uses large datasets to quantify and compare the performance of various techniques.Features and topics include: Ear detection and recognition in 2D image - 3D object recognition and 3D biometrics - 3D ear recognition - Performance comparison and prediction.The techniques discussed will be of great interest to researchers, developers and decision makers who are involved in robust human recognition by computer for a large number of practical applications.

Biometrics deal with recognition of individuals based on their physiological or behavioural characteristics. Researchers have done extensive studies on biometrics such as fingerprint, face, palm print, iris and gait. Ear, a viable new class of biometrics, has certain advantages over face and fingerprint, which are the two most common biometrics in both academic research and industrial applications.This book explores all aspects of 3D ear recognition: representation, detection, recognition, indexing and performance prediction. It uses large datasets to quantify and compare the performance of various techniques.Features and topics include: Ear detection and recognition in 2D image - 3D object recognition and 3D biometrics - 3D ear recognition - Performance comparison and prediction.The techniques discussed will be of great interest to researchers, developers and decision makers who are involved in robust human recognition by computer for a large number of practical applications.

Recently, there has been a dramatic increase in the use of sensors in the non-visible bands. As a result, there is a need for existing computer vision methods and algorithms to be adapted for use with non-visible sensors, or for the development of completely new methods and systems. Computer Vision Beyond the Visible Spectrum is the first book to bring together state-of-the-art work in this area. It presents new & pioneering research across the electromagnetic spectrum in the military, commercial, and medical domains. By providing a detailed examination of each of these areas, it focuses on the development of state-of-the-art algorithms and looks at how they can be used to solve existing & new challenges within computer vision. Essential reading for academics & industrial researchers working in the area of computer vision, image processing, and medical imaging, it will also be useful background reading for advanced undergraduate & postgraduate students.

Recently, there has been a dramatic increase in the use of sensors in the non-visible bands. As a result, there is a need for existing computer vision methods and algorithms to be adapted for use with non-visible sensors, or for the development of completely new methods and systems. Computer Vision Beyond the Visible Spectrum is the first book to bring together state-of-the-art work in this area. It presents new & pioneering research across the electromagnetic spectrum in the military, commercial, and medical domains. By providing a detailed examination of each of these areas, it focuses on the development of state-of-the-art algorithms and looks at how they can be used to solve existing & new challenges within computer vision. Essential reading for academics & industrial researchers working in the area of computer vision, image processing, and medical imaging, it will also be useful background reading for advanced undergraduate & postgraduate students.

The advances of live cell video imaging and high-throughput technologies for functional and chemical genomics provide unprecedented opportunities to understand how biological processes work in subcellularand multicellular systems. The interdisciplinary research field of Video Bioinformatics is defined by BirBhanu as the automated processing, analysis, understanding, data mining, visualization, query-basedretrieval/storage of biological spatiotemporal events/data and knowledge extracted from dynamic imagesand microscopic videos. Video bioinformatics attempts to provide a deeper understanding of continuousand dynamic life processes.Genome sequences alone lack spatial and temporal information, and video imaging of specific moleculesand their spatiotemporal interactions, using a range of imaging methods, are essential to understandhow genomes create cells, how cells constitute organisms, and how errant cells cause disease. The bookexamines interdisciplinary research issues and challenges with examples that deal with organismal dynamics,intercellular and tissue dynamics, intracellular dynamics, protein movement, cell signaling and softwareand databases for video bioinformatics.Topics and Features• Covers a set of biological problems, their significance, live-imaging experiments, theory andcomputational methods, quantifiable experimental results and discussion of results.• Provides automated methods for analyzing mild traumatic brain injury over time, identifying injurydynamics after neonatal hypoxia-ischemia and visualizing cortical tissue changes during seizureactivity as examples of organismal dynamics• Describes techniques for quantifying the dynamics of human embryonic stem cells with examplesof cell detection/segmentation, spreading and other dynamic behaviors which are important forcharacterizing stem cell health• Examines and quantifies dynamic processes in plant and fungal systems such as cell trafficking,growth of pollen tubes in model systems such as Neurospora Crassa and Arabidopsis• Discusses the dynamics of intracellular molecules for DNA repair and the regulation of cofilintransport using video analysis• Discusses software, system and database aspects of video bioinformatics by providing examples of5D cell tracking by FARSIGHT open source toolkit, a survey on available databases and software,biological processes for non-verbal communications and identification and retrieval of moth imagesThis unique text will be of great interest to researchers and graduate students of Electrical Engineering,Computer Science, Bioengineering, Cell Biology, Toxicology, Genetics, Genomics, Bioinformatics, ComputerVision andPattern Recognition, Medical Image Analysis, and Cell Molecular and Developmental Biology.The large number of example applications will also appeal to application scientists and engineers.Dr. Bir Bhanu is Distinguished Professor of Electrical & C omputer Engineering, Interim Chair of theDepartment of Bioengineering, Cooperative Professor of Computer Science & Engineering, and MechanicalEngineering and the Director of the Center for Research in Intelligent Systems, at the University of California,Riverside, California, USA.Dr. Prue Talbot is Professor of Cell Biology & Neuroscience and Director of the Stem Cell Center and Core atthe University of California Riverside, California, USA.

Issues of biometrics security are also examined. Topics and features: addresses the application of deep learning to enhance the performance of biometrics identification across a wide range of different biometrics modalities;

The advances of live cell video imaging and high-throughput technologies for functional and chemical genomics provide unprecedented opportunities to understand how biological processes work in subcellularand multicellular systems. The interdisciplinary research field of Video Bioinformatics is defined by BirBhanu as the automated processing, analysis, understanding, data mining, visualization, query-basedretrieval/storage of biological spatiotemporal events/data and knowledge extracted from dynamic imagesand microscopic videos. Video bioinformatics attempts to provide a deeper understanding of continuousand dynamic life processes.Genome sequences alone lack spatial and temporal information, and video imaging of specific moleculesand their spatiotemporal interactions, using a range of imaging methods, are essential to understandhow genomes create cells, how cells constitute organisms, and how errant cells cause disease. The bookexamines interdisciplinary research issues and challenges with examples that deal with organismal dynamics,intercellular and tissue dynamics, intracellular dynamics, protein movement, cell signaling and softwareand databases for video bioinformatics.Topics and Features• Covers a set of biological problems, their significance, live-imaging experiments, theory andcomputational methods, quantifiable experimental results and discussion of results.• Provides automated methods for analyzing mild traumatic brain injury over time, identifying injurydynamics after neonatal hypoxia-ischemia and visualizing cortical tissue changes during seizureactivity as examples of organismal dynamics• Describes techniques for quantifying the dynamics of human embryonic stem cells with examplesof cell detection/segmentation, spreading and other dynamic behaviors which are important forcharacterizing stem cell health• Examines and quantifies dynamic processes in plant and fungal systems such as cell trafficking,growth of pollen tubes in model systems such as Neurospora Crassa and Arabidopsis• Discusses the dynamics of intracellular molecules for DNA repair and the regulation of cofilintransport using video analysis• Discusses software, system and database aspects of video bioinformatics by providing examples of5D cell tracking by FARSIGHT open source toolkit, a survey on available databases and software,biological processes for non-verbal communications and identification and retrieval of moth imagesThis unique text will be of great interest to researchers and graduate students of Electrical Engineering,Computer Science, Bioengineering, Cell Biology, Toxicology, Genetics, Genomics, Bioinformatics, ComputerVision andPattern Recognition, Medical Image Analysis, and Cell Molecular and Developmental Biology.The large number of example applications will also appeal to application scientists and engineers.Dr. Bir Bhanu is Distinguished Professor of Electrical & C omputer Engineering, Interim Chair of theDepartment of Bioengineering, Cooperative Professor of Computer Science & Engineering, and MechanicalEngineering and the Director of the Center for Research in Intelligent Systems, at the University of California,Riverside, California, USA.Dr. Prue Talbot is Professor of Cell Biology & Neuroscience and Director of the Stem Cell Center and Core atthe University of California Riverside, California, USA.