Search

The first edition of this textbook was published in 2021. Over the past two years, we have invested in enhancing all aspects of deep learning methods to ensure the book is comprehensive and impeccable. Taking into account feedback from our readers and audience, the author has diligently updated this book. The second edition of this textbook presents control theory, transformer models, and graph neural networks (GNN) in deep learning. We have incorporated the latest algorithmic advances and large-scale deep learning models, such as GPTs, to align with the current research trends. Through the second edition, this book showcases how computational methods in deep learning serve as a dynamic driving force in this era of artificial intelligence (AI). This book is intended for research students, engineers, as well as computer scientists with interest in computational methods in deep learning. Furthermore, it is also well-suited for researchers exploring topics such as machine intelligence, robotic control, and related areas.

This book constitutes the proceedings of the 37th International Conference, IVCNZ 2022, which took place in Auckland, New Zealand, in November 2022.The 37 papers (14 accepted for long oral presentation, 23 for short oral presentation) included in this volume were carefully reviewed and selected from 79 submissions. The conference presents papers on all aspects of computer vision, image processing, computer graphics, virtual and augmented reality, visualization, and HCI applications related to these fields.

This book constitutes selected papers from the First International Symposium on Geometry and Vision, ISGV 2021, held in Auckland, New Zealand, in January 2021. Due to the COVID-19 pandemic the conference was held in partially virtual format. The 29 papers were thoroughly reviewed and selected from 50 submissions. They cover topics in areas of digital geometry, graphics, image and video technologies, computer vision, and multimedia technologies.

Integrating concepts from deep learning, machine learning, and artificial neural networks, this highly unique textbook presents content progressively from easy to more complex, orienting its content about knowledge transfer from the viewpoint of machine intelligence. It adopts the methodology from graphical theory, mathematical models, and algorithmic implementation, as well as covers datasets preparation, programming, results analysis and evaluations.Beginning with a grounding about artificial neural networks with neurons and the activation functions, the work then explains the mechanism of deep learning using advanced mathematics. In particular, it emphasizes how to use TensorFlow and the latest MATLAB deep-learning toolboxes for implementing deep learning algorithms.As a prerequisite, readers should have a solid understanding especially of mathematical analysis, linear algebra, numerical analysis, optimizations, differential geometry, manifold, and information theory, as well as basic algebra, functional analysis, and graphical models. This computational knowledge will assist in comprehending the subject matter not only of this text/reference, but also in relevant deep learning journal articles and conference papers.This textbook/guide is aimed at Computer Science research students and engineers, as well as scientists interested in deep learning for theoretic research and analysis. More generally, this book is also helpful for those researchers who are interested in machine intelligence, pattern analysis, natural language processing, and machine vision.Dr. Wei Qi Yan is an Associate Professor in the Department of Computer Science at Auckland University of Technology, New Zealand. His other publications include the Springer title, Visual Cryptography for Image Processing and Security.

This volume constitutes the refereed proceedings, presented during the ACPR 2019 Workshops, held in Auckland, New Zealand, in November 2019. The 17 full papers and 6 short papers were carefully reviewed and selected out of numerous submissions. The papers are organized according to the topics of the workshops: computer vision for modern vehicles; advances and applications on generative deep learning models; image and pattern analysis for multidisciplinary computational anatomy; multi-sensor for action and gesture recognition; towards the automatic data processing chain for airborne and spaceborne sensors.

This two-volume set constitutes the proceedings of the 5th Asian Conference on ACPR 2019, held in Auckland, New Zealand, in November 2019. The 9 full papers presented in this volume were carefully reviewed and selected from 14 submissions. They cover topics such as: classification; action and video and motion; object detection and anomaly detection; segmentation, grouping and shape; face and body and biometrics; adversarial learning and networks; computational photography; learning theory and optimization; applications, medical and robotics; computer vision and robot vision; pattern recognition and machine learning; multi-media and signal processing and interaction.

This practically-oriented textbook introduces the fundamentals of designing digital surveillance systems powered by intelligent computing techniques. The text offers comprehensive coverage of each aspect of the system, from camera calibration and data capture, to the secure transmission of surveillance data, in addition to the detection and recognition of individual biometric features and objects. The coverage concludes with the development of a complete system for the automated observation of the full lifecycle of a surveillance event, enhanced by the use of artificial intelligence and supercomputing technology.This updated third edition presents an expanded focus on human behavior analysis and privacy preservation, as well as deep learning methods.Topics and features: contains review questions and exercises in every chapter, together with a glossary; describes the essentials of implementing an intelligent surveillance system and analyzing surveillance data, including a range of biometric characteristics; examines the importance of network security and digital forensics in the communication of surveillance data, as well as issues of issues of privacy and ethics; discusses the Viola-Jones object detection method, and the HOG algorithm for pedestrian and human behavior recognition; reviews the use of artificial intelligence for automated monitoring of surveillance events, and decision-making approaches to determine the need for human intervention; presents a case study on a system that triggers an alarm when a vehicle fails to stop at a red light, and identifies the vehicle's license plate number; investigates the use of cutting-edge supercomputing technologies for digital surveillance, such as FPGA, GPU and parallel computing.This concise and accessible work serves as a classroom-tested textbook for graduate-level courses on intelligent surveillance. Researchers and engineersinterested in entering this area will also find the book suitable as a helpful self-study reference.