This book focuses on deep learning-based methods for hyperspectral image (HSI) analysis. Unsupervised spectral-spatial adaptive band-noise factor-based formulation is devised for HSI noise detection and band categorization. The method to characterize the bands along with the noise estimation of HSIs will benefit subsequent remote sensing techniques significantly. This book develops on two fronts: On the one hand, it is aimed at domain professionals who want to have an updated overview of how hyperspectral acquisition techniques can combine with deep learning architectures to solve specific tasks in different application fields. On the other hand, the authors want to target the machine learning and computer vision experts by giving them a picture of how deep learning technologies are applied to hyperspectral data from a multidisciplinary perspective. The presence of these two viewpoints and the inclusion of application fields of remote sensing by deep learning are the original contributions of this review, which also highlights some potentialities and critical issues related to the observed development trends.

This book contains the latest computational intelligence methodologies and applications. This book is a collection of selected papers presented at International Conference on Sustainable Computing and Intelligent Systems (SCIS 2021), held in Jaipur, India, during February 5-6, 2021. It includes novel and innovative work from experts, practitioners, scientists, and decision-makers from academia and industry. It covers selected papers in the area of artificial intelligence and intelligent systems, intelligent business systems, machine intelligence, computer vision, Web intelligence, big data analytics, swarm intelligence, and related topics.

With the vast development of Internet capacity and speed, as well as wide adop- tion of media technologies in people's daily life, a large amount of videos have been surging, and need to be efficiently processed or organized based on interest. The human visual perception system could, without difficulty, interpret and r- ognize thousands of events in videos, despite high level of video object clutters, different types of scene context, variability of motion scales, appearance changes, occlusions and object interactions. For a computer vision system, it has been be very challenging to achieve automatic video event understanding for decades. Broadly speaking, those challenges include robust detection of events under - tion clutters, event interpretation under complex scenes, multi-level semantic event inference, putting events in context and multiple cameras, event inference from object interactions, etc. In recent years, steady progress has been made towards better models for video event categorisation and recognition, e. g. , from modelling events with bag of spatial temporal features to discovering event context, from detecting events using a single camera to inferring events through a distributed camera network, and from low-level event feature extraction and description to high-level semantic event classification and recognition. Nowadays, text based video retrieval is widely used by commercial search engines. However, it is still very difficult to retrieve or categorise a specific video segment based on their content in a real multimedia system or in surveillance applications.

This book analyzes the multimodal verbal and nonverbal behavior of humans in both an artificial game, based on the well-known Mafia and Resistance games, as well as selected other settings. This book develops statistical results linking different types of facial expressions (e.g. smile, pursed lips, raised eyebrows), vocal features (e.g., pitch, loudness) and linguistic features (e.g., dominant language, turn length) with both unary behaviors (e.g. is person X lying?) to binary behaviors (Is person X dominant compared to person Y? Does X trust Y? Does X like Y?). In addition, this book describes machine learning and computer vision-based algorithms that can be used to predict deception, as well as the visual focus of attention of people during discussions that can be linked to many binary behaviors. It is written by a multidisciplinary team of both social scientists and computer scientists. Meetings are at the very heart of human activity. Whether you are involved in a business meeting or in a diplomatic negotiation, such an event has multiple actors, some cooperative and some adversarial. Some actors may be deceptive, others may have complex relationships with others in the group. This book consists of a set of 11 chapters that describe the factors that link human behavior in group settings and attitudes to facial and voice characteristics. Researchers working in social sciences (communication, psychology, cognitive science) with an interest in studying the link between human interpersonal behavior and facial/speech/linguistic characteristics will be interested in this book. Computer scientists, who are interested in developing machine learning and deep learning based models of human behavior in group settings will also be interested in purchasing this book.

Principles of Image Printing Technology is a unique review of technology use in the printing industry since the time of the medieval engravers and busy newsroom typesetters. It provides a historical review of the advancement of technology and describes in-depth both technical fundamentals and industrial procedures. Intended primarily for students in graphic communications programs, this book includes all the necessary background for understanding printing technology. In addition, by providing findings from basic research studies and industrial processes that have been omitted elsewhere in published volumes, it offers a useful guide to researchers and professionals in the printing industry.

This book is a collection of research papers selected for presentation at the International Conference on Smart Computational Methods in Continuum Mechanics 2021, organized by Moscow Institute of Physics and Technology and the Institute for Computer Aided Design of Russian Academy of Sciences. The work is presented in two volumes. The primary objective of the book is to report the state-of-the-art on smart computational paradigms in continuum mechanics and explore the use of artificial intelligence paradigms such as neural nets, and machine learning for improving the performance of the designed engineering systems. The book includes up-to-date smart computational methods which are used to solve problems in continuum mechanics, engineering, seismic prospecting, non-destructive testing, and so on. The main features of the book are the research papers on the application of novel smart methods including neural nets and machine learning, computational algorithms, smart software systems, and high-performance computer systems for solving complex engineering problems. The case studies pertaining to the real-world applications in the above fields are included. The book presents a collection of best research papers in English language from some of the world leaders in the field of smart system modelling and design of engineering systems.

This book constitutes the refereed proceedings of the 11th IFIP TC 12 International Conference on Intelligent Information Processing, IIP 2020, held in Hangzhou, China, in July 2020. The 24 full papers and 5 short papers presented were carefully reviewed and selected from 36 submissions. They are organized in topical sections on machine learning; multi-agent system; recommendation system; social computing; brain computer integration; pattern recognition; and computer vision and image understanding.

Inverse problems such as imaging or parameter identification deal with the recovery of unknown quantities from indirect observations, connected via a model describing the underlying context. While traditionally inverse problems are formulated and investigated in a static setting, we observe a significant increase of interest in time-dependence in a growing number of important applications over the last few years. Here, time-dependence affects a) the unknown function to be recovered and / or b) the observed data and / or c) the underlying process. Challenging applications in the field of imaging and parameter identification are techniques such as photoacoustic tomography, elastography, dynamic computerized or emission tomography, dynamic magnetic resonance imaging, super-resolution in image sequences and videos, health monitoring of elastic structures, optical flow problems or magnetic particle imaging to name only a few. Such problems demand for innovation concerning their mathematical description and analysis as well as computational approaches for their solution.

This book covers the essential concepts and strategies within traditional and cutting-edge feature learning methods thru both theoretical analysis and case studies. Good features give good models and it is usually not classifiers but features that determine the effectiveness of a model. In this book, readers can find not only traditional feature learning methods, such as principal component analysis, linear discriminant analysis, and geometrical-structure-based methods, but also advanced feature learning methods, such as sparse learning, low-rank decomposition, tensor-based feature extraction, and deep-learning-based feature learning. Each feature learning method has its own dedicated chapter that explains how it is theoretically derived and shows how it is implemented for real-world applications. Detailed illustrated figures are included for better understanding. This book can be used by students, researchers, and engineers looking for a reference guide for popular methods of feature learning and machine intelligence.

This book provides insights into the state of the art of digital cultural heritage using computer graphics, image processing, computer vision, visualization and reconstruction, virtual and augmented reality and serious games. It aims at covering the emergent approaches for digitization and preservation of Cultural Heritage, both in its tangible and intangible facets. Advancements in Digital Cultural Heritage research have been abundant in recent years covering a wide assortment of topics, ranging from visual data acquisition, pre-processing, classification, analysis and synthesis, 3D modelling and reconstruction, semantics and symbolic representation, metadata description, repository and archiving, to new forms of interactive and personalized presentation, visualization and immersive experience provision via advanced computer graphics, interactive virtual and augmented environments, serious games and digital storytelling. Different aspects pertaining to visual computing with regard to tangible (books, images, paintings, manuscripts, uniforms, maps, artefacts, archaeological sites, monuments) and intangible (e.g. dance and performing arts, folklore, theatrical performances) cultural heritage preservation, documentation, protection and promotion are covered, including rendering and procedural modelling of cultural heritage assets, keyword spotting in old documents, drone mapping and airborne photogrammetry, underwater recording and reconstruction, gamification, visitor engagement, animated storytelling, analysis of choreographic patterns, and many more. The book brings together and targets researchers from the domains of computing, engineering, archaeology and the arts, and aims at underscoring the potential for cross-fertilization and collaboration among these communities.

This three-volume set (CCIS 1376-1378) constitutes the refereed proceedings of the 5th International Conference on Computer Vision and Image Processing, CVIP 2020, held in Prayagraj, India, in December 2020. Due to the COVID-19 pandemic the conference was partially held online. The 134 papers papers were carefully reviewed and selected from 352 submissions. The papers present recent research on such topics as biometrics, forensics, content protection, image enhancement/super-resolution/restoration, motion and tracking, image or video retrieval, image, image/video processing for autonomous vehicles, video scene understanding, human-computer interaction, document image analysis, face, iris, emotion, sign language and gesture recognition, 3D image/video processing, action and event detection/recognition, medical image and video analysis, vision-based human GAIT analysis, remote sensing, and more.

This volume constitutes the revised selected papers of the 15th International Conference on Bio-inspired Computing: Theories and Applications, BIC-TA 2020, held in Qingdao, China, in October 2020.The 43 full papers presented in both volumes were selected from 109 submissions. The papers are organized according to the topical headings: evolutionary computation and swarm intelligence; neural networks and machine learning; DNA computing and membrane computing.

The last half century has seen the development of many biological or physical t- ories that have explicitly or implicitly involved medial descriptions of objects and other spatial entities in our world. Simultaneously mathematicians have studied the properties of these skeletal descriptions of shape, and, stimulated by the many areas where medial models are useful, computer scientists and engineers have developed numerous algorithms for computing and using these models. We bring this kno- edge and experience together into this book in order to make medial technology more widely understood and used. The book consists of an introductory chapter, two chapters on the major mat- matical results on medial representations, ?ve chapters on algorithms for extracting medial models from boundary or binary image descriptions of objects, and three chapters on applications in image analysis and other areas of study and design. We hope that this book will serve the science and engineering communities using medial models and will provide learning material for students entering this ?eld. We are fortunate to have recruited many of the world leaders in medial theory, algorithms, and applications to write chapters in this book. We thank them for their signi?cant effort in preparing their contributions. We have edited these chapters and have combined them with the ?ve chapters that we have written to produce an integrated whole.

This book analyzes techniques that use the direct and inverse fuzzy transform for image processing and data analysis. The book is divided into two parts, the first of which describes methods and techniques that use the bi-dimensional fuzzy transform method in image analysis. In turn, the second describes approaches that use the multidimensional fuzzy transform method in data analysis. An F-transform in one variable is defined as an operator which transforms a continuous function f on the real interval [a,b] in an n-dimensional vector by using n-assigned fuzzy sets A1, ... , An which constitute a fuzzy partition of [a,b]. Then, an inverse F-transform is defined in order to convert the n-dimensional vector output in a continuous function that equals f up to an arbitrary quantity . We may limit this concept to the finite case by defining the discrete F-transform of a function f in one variable, even if it is not known a priori. A simple extension of this concept to functions in two variables allows it to be used for the coding/decoding and processing of images. Moreover, an extended version with multidimensional functions can be used to address a host of topics in data analysis, including the analysis of large and very large datasets. Over the past decade, many researchers have proposed applications of fuzzy transform techniques for various image processing topics, such as image coding/decoding, image reduction, image segmentation, image watermarking and image fusion; and for such data analysis problems as regression analysis, classification, association rule extraction, time series analysis, forecasting, and spatial data analysis. The robustness, ease of use, and low computational complexity of fuzzy transforms make them a powerful fuzzy approximation tool suitable for many computer science applications. This book presents methods and techniques based on the use of fuzzy transforms in various applications of image processing and data analysis, including image segmentation, image tamper detection, forecasting, and classification, highlighting the benefits they offer compared with traditional methods. Emphasis is placed on applications of fuzzy transforms to innovative problems, such as massive data mining, and image and video security in social networks based on the application of advanced fragile watermarking systems. This book is aimed at researchers, students, computer scientists and IT developers to acquire the knowledge and skills necessary to apply and implement fuzzy transforms-based techniques in image and data analysis applications.

This book addresses one of the most important unsolved problems in artificial intelligence: the task of learning, in an unsupervised manner, from massive quantities of spatiotemporal visual data that are available at low cost. The book covers important scientific discoveries and findings, with a focus on the latest advances in the field. Presenting a coherent structure, the book logically connects novel mathematical formulations and efficient computational solutions for a range of unsupervised learning tasks, including visual feature matching, learning and classification, object discovery, and semantic segmentation in video. The final part of the book proposes a general strategy for visual learning over several generations of student-teacher neural networks, along with a unique view on the future of unsupervised learning in real-world contexts. Offering a fresh approach to this difficult problem, several efficient, state-of-the-art unsupervised learning algorithms are reviewed in detail, complete with an analysis of their performance on various tasks, datasets, and experimental setups. By highlighting the interconnections between these methods, many seemingly diverse problems are elegantly brought together in a unified way. Serving as an invaluable guide to the computational tools and algorithms required to tackle the exciting challenges in the field, this book is a must-read for graduate students seeking a greater understanding of unsupervised learning, as well as researchers in computer vision, machine learning, robotics, and related disciplines.

This two-volume set constitutes the refereed proceedings of the Third International Conference on Recent Trends in Image Processing and Pattern Recognition (RTIP2R) 2020, held in Aurangabad, India, in January 2020.The 78 revised full papers presented were carefully reviewed and selected from 329 submissions. The papers are organized in topical sections in the two volumes. Part I: Computer vision and applications; Data science and machine learning; Document understanding and Recognition. Part II: Healthcare informatics and medical imaging; Image analysis and recognition; Signal processing and pattern recognition; Image and signal processing in Agriculture.

This three-volume set (CCIS 1367-1368) constitutes the refereed proceedings of the 5th International Conference on Computer Vision and Image Processing, CVIP 2020, held in Prayagraj, India, in December 2020. Due to the COVID-19 pandemic the conference was partially held online. The 134 papers papers were carefully reviewed and selected from 352 submissions. The papers present recent research on such topics as biometrics, forensics, content protection, image enhancement/super-resolution/restoration, motion and tracking, image or video retrieval, image, image/video processing for autonomous vehicles, video scene understanding, human-computer interaction, document image analysis, face, iris, emotion, sign language and gesture recognition, 3D image/video processing, action and event detection/recognition, medical image and video analysis, vision-based human GAIT analysis, remote sensing, and more.

This book describes various types of image patterns for image retrieval. All these patterns are texture dependent. Few image patterns such as Improved directional local extrema patterns, Local Quantized Extrema Patterns, Local Color Oppugnant Quantized Extrema Patterns and Local Mesh quantized extrema patterns are presented. Inter-relationships among the pixels of an image are used for feature extraction. In contrast to the existing patterns these patterns focus on local neighborhood of pixels to creates the feature vector. Evaluation metrics such as precision and recall are calculated after testing with standard databases i.e., Corel-1k, Corel-5k and MIT VisTex database. This book serves as a practical guide for students and researchers. -The text introduces two models of Directional local extrema patterns viz., Integration of color and directional local extrema patterns Integration of Gabor features and directional local extrema patterns. -Provides a framework to extract the features using quantization method -Discusses the local quantized extrema collected from two oppugnant color planes -Illustrates the mesh structure with the pixels at alternate positions.

This book attempts to improve algorithms by novel theories and complex data analysis in different scopes including object detection, remote sensing, data transmission, data fusion, gesture recognition, and edical image processing and analysis. The book is directed to the Ph.D. students, professors, researchers, and software developers working in the areas of digital video processing and computer vision technologies.

This book gathers selected papers presented at the Third International Symposium on Signal and Image Processing (ISSIP 2020), organized by the Department of Information Technology, RCC Institute of Information Technology, Kolkata, during March 18-19, 2020. It presents fascinating, state-of-the-art research findings in the field of signal and image processing. It includes conference papers covering a wide range of signal processing applications involving filtering, encoding, classification, segmentation, clustering, feature extraction, denoising, watermarking, object recognition, reconstruction and fractal analysis. It addresses various types of signals, such as image, video, speech, non-speech audio, handwritten text, geometric diagram, ECG and EMG signals; MRI, PET and CT scan images; THz signals; solar wind speed signals (SWS); and photoplethysmogram (PPG) signals, and demonstrates how new paradigms of intelligent computing, like quantum computing, can be applied to process and analyze signals precisely and effectively.

This book provides a framework for robust and novel biometric techniques, along with implementation and design strategies. The theory, principles, pragmatic and modern methods, and future directions of biometrics are presented, along with in-depth coverage of biometric applications in driverless cars, automated and AI-based systems, IoT, and wearable devices. Additional coverage includes computer vision and pattern recognition, cybersecurity, cognitive computing, soft biometrics, and the social impact of biometric technology. The book will be a valuable reference for researchers, faculty, and practicing professionals working in biometrics and related fields, such as image processing, computer vision, and artificial intelligence. Highlights robust and novel biometrics techniques Provides implementation strategies and future research directions in the field of biometrics Includes case studies and emerging applications

In today's world, deep learning source codes and a plethora of open access geospatial images are readily available and easily accessible. However, most people are missing the educational tools to make use of this resource. Deep Learning for Remote Sensing Images with Open Source Software is the first practical book to introduce deep learning techniques using free open source tools for processing real world remote sensing images. The approaches detailed in this book are generic and can be adapted to suit many different applications for remote sensing image processing, including landcover mapping, forestry, urban studies, disaster mapping, image restoration, etc. Written with practitioners and students in mind, this book helps link together the theory and practical use of existing tools and data to apply deep learning techniques on remote sensing images and data. Specific Features of this Book: The first book that explains how to apply deep learning techniques to public, free available data (Spot-7 and Sentinel-2 images, OpenStreetMap vector data), using open source software (QGIS, Orfeo ToolBox, TensorFlow) Presents approaches suited for real world images and data targeting large scale processing and GIS applications Introduces state of the art deep learning architecture families that can be applied to remote sensing world, mainly for landcover mapping, but also for generic approaches (e.g. image restoration) Suited for deep learning beginners and readers with some GIS knowledge. No coding knowledge is required to learn practical skills. Includes deep learning techniques through many step by step remote sensing data processing exercises.

The book discusses major technical advances and research findings in the field of machine intelligence in medical image analysis. It examines the latest technologies and that have been implemented in clinical practice, such as computational intelligence in computer-aided diagnosis, biological image analysis, and computer-aided surgery and therapy. This book provides insights into the basic science involved in processing, analysing, and utilising all aspects of advanced computational intelligence in medical decision-making based on medical imaging.

This book presents studies involving algorithms in the machine learning paradigms. It discusses a variety of learning problems with diverse applications, including prediction, concept learning, explanation-based learning, case-based (exemplar-based) learning, statistical rule-based learning, feature extraction-based learning, optimization-based learning, quantum-inspired learning, multi-criteria-based learning and hybrid intelligence-based learning.

A timely and authoritative guide to the state of the art of wave scattering

Scattering of Electromagnetic Waves offers in three volumes a complete and up-to-date treatment of wave scattering by random discrete scatterers and rough surfaces. Written by leading scientists who have made important contributions to wave scattering over three decades, this new work explains the principles, methods, and applications of this rapidly expanding, interdisciplinary field. It covers both introductory and advanced material and provides students and researchers in remote sensing as well as imaging, optics, and electromagnetic theory with a one-stop reference to a wealth of current research results. Plus, Scattering of Electromagnetic Waves contains detailed discussions of both analytical and numerical methods, including cutting-edge techniques for the recovery of earth/land parametric information.

The three volumes are entitled respectively Theories and Applications, Numerical Simulation, and Advanced Topics. In the third volume, Advanced Topics, Leung Tsang (University of Washington) and Jin Au Kong (MIT), cover:

• Two-dimensional random rough surface scattering
• Kirchhoff and related methods for rough surface scattering
• Analytic theory of volume scattering based on cascading of layers
• Analytic wave theory for medium with permittivity fluctuations
• Multiple scattering theory for discrete scatterers
• Quasicrystalline approximation in dense media scattering
• Dense media scattering
• Backscattering enhancement