The two-volume set LNCS 10484 and 10485 constitutes the refereed proceedings of the 19th International Conference on Image Analysis and Processing, ICIAP 2017, held in Catania, Italy, in September 2017. The 138 papers presented were carefully reviewed and selected from 229 submissions. The papers cover both classic and the most recent trends in image processing, computer vision, and pattern recognition, addressing both theoretical and applicative aspects. They are organized in the following topical sections: video analysis and understanding; pattern recognition and machine learning; multiview geometry and 3D computer vision; image analysis, detection and recognition; multimedia; biomedical and assistive technology; information forensics and security; imaging for cultural heritage and archaeology; and imaging solutions for improving the quality of life.
The two-volume set LNCS 10484 and 10485 constitutes the refereed proceedings of the 19th International Conference on Image Analysis and Processing, ICIAP 2017, held in Catania, Italy, in September 2017. The 138 papers presented were carefully reviewed and selected from 229 submissions. The papers cover both classic and the most recent trends in image processing, computer vision, and pattern recognition, addressing both theoretical and applicative aspects. They are organized in the following topical sections: video analysis and understanding; pattern recognition and machine learning; multiview geometry and 3D computer vision; image analysis, detection and recognition; multimedia; biomedical and assistive technology; information forensics and security; imaging for cultural heritage and archaeology; and imaging solutions for improving the quality of life.
This book constitutes the refereed proceedings of seven workshops held at the 19th International Conference on Image Analysis and Processing, ICIAP 2017, in Catania, Italy, in September 2017: First International Workshop on Brain-Inspired Computer Vision – WBICV 2017; Social Signal Processing and Beyond - SSPandBE 2017; Automatic affect analysis and synthesis - 3AS 2017; Background learning for detection and tracking from RGBD Videos - RGBD 2017; Natural human-computer Interaction and ecological perception in immersive Virtual and Augmented Reality - NIVAR 2017; 1st International Workshop on Biometrics as-a-service: cloud-based technology, systems and applications - IWBAAS 2017; 3rd International Workshop on Multimedia Assisted Dietary Management - MADiMa 2017.
This comprehensive textbook presents a broad review of both traditional (i.e., conventional) and deep learning aspects of object detection in various adversarial real-world conditions in a clear, insightful, and highly comprehensive style. Beginning with the relation of computer vision and object detection, the text covers the various representation of objects, applications of object detection, and real-world challenges faced by the research community for object detection task. The book addresses various real-world degradations and artifacts for the object detection task and also highlights the impacts of artifacts in the object detection problems. The book covers various imaging modalities and benchmark datasets mostly adopted by the research community for solving various aspects of object detection tasks. The book also collects together solutions and perspectives proposed by the preeminent researchers in the field, addressing not only the background of visibility enhancement but also techniques proposed in the literature for visibility enhancement of scenes and detection of objects in various representative real-world challenges. Computer Vision: Object Detection in Adversarial Vision is unique for its diverse content, clear presentation, and overall completeness. It provides a clear, practical, and detailed introduction and advancement of object detection in various representative challenging real-world conditions. Topics and Features: • Offers the first truly comprehensive presentation of aspects of the object detection in degraded and nondegraded environment. • Includes in-depth discussion of various degradation and artifacts, and impact of those artifacts in the real world on solving the object detection problems. • Gives detailed visual examples of applications of object detection in the real world. • Presents a detailed description of popular imaging modalities for object detection adopted by researchers. • Presents the key characteristics of various benchmark datasets in indoor and outdoor environment for solving object detection tasks. • Surveys the complete field of visibility enhancement of degraded scenes, including conventional methods designed for enhancing the degraded scenes as well as the deep architectures. • Discusses techniques for detection of objects in real-world applications. • Contains various hands-on practical examples and a tutorial for solving object detection problems using Python. • Motivates readers to build vision-based systems for solving object detection problems in degraded and nondegraded real-world challenges. The book will be of great interest to a broad audience ranging from researchers and practitioners to graduate and postgraduate students involved in computer vision tasks with respect to object detection in degraded and nondegraded real-world vision problems.
This book presents the latest developments concerning techniques, tools, and methodologies in supply chain ecosystems. It gathers contributions from a variety of experts, who analyze a range of case studies and industrial sectors such as manufacturing, energy, agricultural, healthcare, humanitarian logistics, and urban goods distribution, to name but a few. The book is chiefly intended to meet the needs of two sectors: firstly, the academic sector, so as to familiarize students, professors, and researchers with the tools that are now being used to optimize supply chains; and secondly, the industrial and managerial sector, so that supply chain management practitioners can benefit from methods and tools that are yielding valuable results in other contexts.
This is an open access book. The first international Conference on Advances in Computer Vision and Artificial Intelligence Technologies (ACVAIT 2022) is a biennial conference organized by Department of Computer Science and Information Technology, Dr. Babasaheb Ambedkar Marathwada University, Aurangabad (MS) India, during August 1–2, 2022. ACVAIT 2022, is dedicated towards advances in the theme areas of Computer Vision, Image Processing, Pattern Recognition, Artificial Intelligence, Machine Learning, Human Computer Interactions, Biomedical Image Processing, Geospatial Technology, Hyperspectral image processing and allied technologies but not limited to. ACVAIT 2022, invites young and/or advanced researchers contributing in the theme area of the conference and also provide them platform for discussing their scientific contributions / research findings with the domain experts, exchange ideas with them and foster closer collaboration between members from the top universities / Higher Education Institutes (HEI). ACVAIT 2022, inviting domain specific work from research scholars, academician, machine learning & AI scientist, industry experts to contribute their scientific contribution in the following areas but not limited to. • Shape representation• Biometrics: face matching, iris recognition, footprint verification and many more.• Statistical, Structural and syntactic pattern recognition• Brain Computer Interface and Human Computer Interactions• Feature extraction and reduction• Biomedical Image Processing• Color and texture analysis• Speech analysis and understanding• Image segmentation• Speaker verification & Synthesis• Image compression, coding and encryption• Clustering and classification• Object recognition, scene understanding and video analytics• Machine learning algorithms • Image matching (pattern matching)• Extreme learning machine• Content based image retrieval and indexing• Artificial Intelligence Trends in Deep learning• Optical character recognition• Big data• Image & Video Forensics• Information retrieval• Pattern recognition and machine learning for Internet of Things• Data mining and Data Analytics• Pattern classification through Sensors• Pattern Recognition for Hyper Spectral Imaging• Satellite Image Processing
This book is open access. Media forensics has never been more relevant to societal life. Not only media content represents an ever-increasing share of the data traveling on the net and the preferred communications means for most users, it has also become integral part of most innovative applications in the digital information ecosystem that serves various sectors of society, from the entertainment, to journalism, to politics. Undoubtedly, the advances in deep learning and computational imaging contributed significantly to this outcome. The underlying technologies that drive this trend, however, also pose a profound challenge in establishing trust in what we see, hear, and read, and make media content the preferred target of malicious attacks. In this new threat landscape powered by innovative imaging technologies and sophisticated tools, based on autoencoders and generative adversarial networks, this book fills an important gap. It presents a comprehensive review of state-of-the-art forensics capabilities that relate to media attribution, integrity and authenticity verification, and counter forensics. Its content is developed to provide practitioners, researchers, photo and video enthusiasts, and students a holistic view of the field.
This book gathers the proceedings of the 10th International Conference on Frontier Computing, held in Singapore, on July 10–13, 2020, and provides comprehensive coverage of the latest advances and trends in information technology, science, and engineering. It addresses a number of broad themes, including communication networks, business intelligence and knowledge management, web intelligence, and related fields that inspire the development of information technology. The respective contributions cover a wide range of topics: database and data mining, networking and communications, web and Internet of things, embedded systems, soft computing, social network analysis, security and privacy, optical communication, and ubiquitous/pervasive computing. Many of the papers outline promising future research directions, and the book benefits students, researchers, and professionals alike. Further, it offers a useful reference guide for newcomers to the field.
This book offers to readers a selection of refereed papers that were presented at the Sixth International Symposium on Intelligent Systems Technologies and Applications (ISTA’20). All submissions were evaluated on the basis of their significance, novelty, and technical quality. This book consists of 28 papers (19 regular and 9 short papers) that were virtually presented at the Symposium. The papers cover different areas such as big data analytics, security and privacy, Internet of things, machine and deep learning, health informatics, visual computing, signal processing, and natural language processing. The book is directed to the researchers and scientists engaged in various fields of intelligent systems.
At the dawn of the 4th Industrial Revolution, the field of Deep Learning (a sub-field of Artificial Intelligence and Machine Learning) is growing continuously and rapidly, developing both theoretically and towards applications in increasingly many and diverse other disciplines. The book at hand aims at exposing its reader to some of the most significant recent advances in deep learning-based technological applications and consists of an editorial note and an additional fifteen (15) chapters. All chapters in the book were invited from authors who work in the corresponding chapter theme and are recognized for their significant research contributions. In more detail, the chapters in the book are organized into six parts, namely (1) Deep Learning in Sensing, (2) Deep Learning in Social Media and IOT, (3) Deep Learning in the Medical Field, (4) Deep Learning in Systems Control, (5) Deep Learning in Feature Vector Processing, and (6) Evaluation of Algorithm Performance. This research book is directed towards professors, researchers, scientists, engineers and students in computer science-related disciplines. It is also directed towards readers who come from other disciplines and are interested in becoming versed in some of the most recent deep learning-based technological applications. An extensive list of bibliographic references at the end of each chapter guides the readers to probe deeper into their application areas of interest.
