Graph Based Methods In Computer Vision Developments And Applications

Computer vision, the science and technology of machines that see, has been a rapidly developing research area since the mid-1970s. It focuses on the understanding of digital input images in many forms, including video and 3-D range data. Graph-Based Methods in Computer Vision: Developments and Applications presents a sampling of the research issues related to applying graph-based methods in computer vision. These methods have been under-utilized in the past, but use must now be increased because of their ability to naturally and effectively represent image models and data. This publication explores current activity and future applications of this fascinating and ground-breaking topic.

This book presents novel graph-theoretic methods for complex computer vision and pattern recognition tasks. It presents the application of graph theory to low-level processing of digital images, presents graph-theoretic learning algorithms for high-level computer vision and pattern recognition applications, and provides detailed descriptions of several applications of graph-based methods to real-world pattern recognition tasks.

This book constitutes the refereed proceedings of the 10th IAPR-TC-15 International Workshop on Graph-Based Representations in Pattern Recognition, GbRPR 2015, held in Beijing, China, in May 2015. The 36 papers presented in this volume were carefully reviewed and selected from 53 submissions. The accepted papers cover diverse issues of graph-based methods and applications, with 7 in graph representation, 15 in graph matching, 7 in graph clustering and classification, and 7 in graph-based applications.

Many computer vision applications such as image filtering, segmentation and stereovision can be formulated as optimization problems. Recently discrete, convex, globally optimal methods have received a lot of attention. Many graph-based methods suffer from metrication artefacts, segmented contours are blocky in areas where contour information is lacking. In the first part of this work, we develop a discrete yet isotropic energy minimization formulation for the continuous maximum flow problem that prevents metrication errors. This new convex formulation leads us to a provably globally optimal solution. The employed interior point method can optimize the problem faster than the existing continuous methods. The energy formulation is then adapted and extended to multi-label problems, and shows improvements over existing methods. Fast parallel proximal optimization tools have been tested and adapted for the optimization of this problem. In the second part of this work, we introduce a framework that generalizes several state-of-the-art graph-based segmentation algorithms, namely graph cuts, random walker, shortest paths, and watershed. This generalization allowed us to exhibit a new case, for which we developed a globally optimal optimization method, named "Power watershed''. Our proposed power watershed algorithm computes a unique global solution to multi labeling problems, and is very fast. We further generalize and extend the framework to applications beyond image segmentation, for example image filtering optimizing an L0 norm energy, stereovision and fast and smooth surface reconstruction from a noisy cloud of 3D points.

Covering the theoretical aspects of image processing and analysis through the use of graphs in the representation and analysis of objects, Image Processing and Analysis with Graphs: Theory and Practice also demonstrates how these concepts are indispensible for the design of cutting-edge solutions for real-world applications. Explores new applications in computational photography, image and video processing, computer graphics, recognition, medical and biomedical imaging With the explosive growth in image production, in everything from digital photographs to medical scans, there has been a drastic increase in the number of applications based on digital images. This book explores how graphs—which are suitable to represent any discrete data by modeling neighborhood relationships—have emerged as the perfect unified tool to represent, process, and analyze images. It also explains why graphs are ideal for defining graph-theoretical algorithms that enable the processing of functions, making it possible to draw on the rich literature of combinatorial optimization to produce highly efficient solutions. Some key subjects covered in the book include: Definition of graph-theoretical algorithms that enable denoising and image enhancement Energy minimization and modeling of pixel-labeling problems with graph cuts and Markov Random Fields Image processing with graphs: targeted segmentation, partial differential equations, mathematical morphology, and wavelets Analysis of the similarity between objects with graph matching Adaptation and use of graph-theoretical algorithms for specific imaging applications in computational photography, computer vision, and medical and biomedical imaging Use of graphs has become very influential in computer science and has led to many applications in denoising, enhancement, restoration, and object extraction. Accounting for the wide variety of problems being solved with graphs in image processing and computer vision, this book is a contributed volume of chapters written by renowned experts who address specific techniques or applications. This state-of-the-art overview provides application examples that illustrate practical application of theoretical algorithms. Useful as a support for graduate courses in image processing and computer vision, it is also perfect as a reference for practicing engineers working on development and implementation of image processing and analysis algorithms.

While labeled data is expensive to prepare, ever increasing amounts of unlabeled data is becoming widely available. In order to adapt to this phenomenon, several semi-supervised learning (SSL) algorithms, which learn from labeled as well as unlabeled data, have been developed. In a separate line of work, researchers have started to realize that graphs provide a natural way to represent data in a variety of domains. Graph-based SSL algorithms, which bring together these two lines of work, have been shown to outperform the state-of-the-art in many applications in speech processing, computer vision, natural language processing, and other areas of Artificial Intelligence. Recognizing this promising and emerging area of research, this synthesis lecture focuses on graph-based SSL algorithms (e.g., label propagation methods). Our hope is that after reading this book, the reader will walk away with the following: (1) an in-depth knowledge of the current state-of-the-art in graph-based SSL algorithms, and the ability to implement them; (2) the ability to decide on the suitability of graph-based SSL methods for a problem; and (3) familiarity with different applications where graph-based SSL methods have been successfully applied. Table of Contents: Introduction / Graph Construction / Learning and Inference / Scalability / Applications / Future Work / Bibliography / Authors' Biographies / Index

Graph-structured data is ubiquitous throughout the natural and social sciences, from telecommunication networks to quantum chemistry. Building relational inductive biases into deep learning architectures is crucial for creating systems that can learn, reason, and generalize from this kind of data. Recent years have seen a surge in research on graph representation learning, including techniques for deep graph embeddings, generalizations of convolutional neural networks to graph-structured data, and neural message-passing approaches inspired by belief propagation. These advances in graph representation learning have led to new state-of-the-art results in numerous domains, including chemical synthesis, 3D vision, recommender systems, question answering, and social network analysis. This book provides a synthesis and overview of graph representation learning. It begins with a discussion of the goals of graph representation learning as well as key methodological foundations in graph theory and network analysis. Following this, the book introduces and reviews methods for learning node embeddings, including random-walk-based methods and applications to knowledge graphs. It then provides a technical synthesis and introduction to the highly successful graph neural network (GNN) formalism, which has become a dominant and fast-growing paradigm for deep learning with graph data. The book concludes with a synthesis of recent advancements in deep generative models for graphs—a nascent but quickly growing subset of graph representation learning.

This present book includes a set of selected revised and extended versions of the best papers presented at the 11th International Joint Conference on Computational Intelligence (IJCCI 2019) – held in Vienna, Austria, from 17 to 19 September 2019. The authors focus on three outstanding fields of Computational Intelligence through the selected panel, namely Evolutionary Computation, Fuzzy Computation and Neural Computation. Besides presenting the recent advances of the selected areas, the book aims to aggregate new and innovative solutions for confirmed researchers and, on the other hand, to provide a source of information and/or inspiration for young interested researchers or learners in the ever-expanding and current filed of Computational Intelligence. It constitutes a precious provision of knowledge for individual researchers as well as represents a valuable sustenance for collective use in academic libraries (of universities and engineering schools) relating innovative techniques in various fields of applications.