These twenty-three contributions focus on the most recent developments in the rapidly evolving field of geometric invariants and their application to computer vision. The introduction summarizes the basics of invariant theory, discusses how invariants are related to problems in computer vision, and looks at the future possibilities, particularly the notion that invariant analysis might provide a solution to the elusive problem of recognizing general curved 3D objects from an arbitrary viewpoint. The remaining chapters consist of original papers that present important developments as well as tutorial articles that provide useful background material. These chapters are grouped into categories covering algebraic invariants, nonalgebraic invariants, invariants of multiple views, and applications. An appendix provides an extensive introduction to projective geometry and its applications to basic problems in computer vision.

A basic problem in computer vision is to understand the structure of a real world scene given several images of it. Techniques for solving this problem are taken from projective geometry and photogrammetry. Here, the authors cover the geometric principles and their algebraic representation in terms of camera projection matrices, the fundamental matrix and the trifocal tensor. The theory and methods of computation of these entities are discussed with real examples, as is their use in the reconstruction of scenes from multiple images. The new edition features an extended introduction covering the key ideas in the book (which itself has been updated with additional examples and appendices) and significant new results which have appeared since the first edition. Comprehensive background material is provided, so readers familiar with linear algebra and basic numerical methods can understand the projective geometry and estimation algorithms presented, and implement the algorithms directly from the book.

This book is the proceedings of the Second Joint European-US Workshop on Applications of Invariance to Computer Vision, held at Ponta Delgada, Azores, Portugal in October 1993. The book contains 25 carefully refereed papers by distinguished researchers. The papers cover all relevant foundational aspects of geometric and algebraic invariance as well as applications to computer vision, particularly to recovery and reconstruction, object recognition, scene analysis, robotic navigation, and statistical analysis. In total, the collection of papers, together with an introductory survey by the editors, impressively documents that geometry, in its different variants, is the most successful and ubiquitous tool in computer vision.

This book was conceived from the realization that there was a need to update recent work on invariants in a single volume providing a useful set of references and pointers to related work. Since the publication in 1992 of J L Mundy and A Zisserman's Geometric Invariance in Computer Vision, the subject has been evolving rapidly. New approaches to invariants have been proposed and novel ways of defining and applying invariants to practical problem solving are testimony to the fundamental importance of the study of invariants to machine vision. This book represents a snapshot of current research around the world. A version of this collection of papers has appeared in the International Journal of Pattern Recognition and Artificial Intelligence (December 1999). The papers in this book are extended versions of the original material published in the journal. They are organized into two categories: foundations and applications. Foundation papers present new ways of defining or analyzing invariants, andapplication papers present novel ways in which known invariant theory is extended and effectively applied to real-world problems in interesting and difficult contexts. Each category contains roughly half of the papers, but there is considerable overlap. All papers carry an element of novelty and generalization that will be useful to theoreticians and practitioners alike. It is hoped that this volume will be not only useful but also inspirational to researchers in image processing, pattern recognition and computer vision at large.

This monograph by one of the world's leading vision researchers provides a thorough, mathematically rigorous exposition of a broad and vital area in computer vision: the problems and techniques related to three-dimensional (stereo) vision and motion. The emphasis is on using geometry to solve problems in stereo and motion, with examples from navigation and object recognition. Faugeras takes up such important problems in computer vision as projective geometry, camera calibration, edge detection, stereo vision (with many examples on real images), different kinds of representations and transformations (especially 3-D rotations), uncertainty and methods of addressing it, and object representation and recognition. His theoretical account is illustrated with the results of actual working programs.Three-Dimensional Computer Vision proposes solutions to problems arising from a specific robotics scenario in which a system must perceive and act. Moving about an unknown environment, the system has to avoid static and mobile obstacles, build models of objects and places in order to be able to recognize and locate them, and characterize its own motion and that of moving objects, by providing descriptions of the corresponding three-dimensional motions. The ideas generated, however, can be used indifferent settings, resulting in a general book on computer vision that reveals the fascinating relationship of three-dimensional geometry and the imaging process.

In image processing, "motions by curvature" provide an efficient way to smooth curves representing the boundaries of objects. In such a motion, each point of the curve moves, at any instant, with a normal velocity equal to a function of the curvature at this point. This book is a rigorous and self-contained exposition of the techniques of "motion by curvature". The approach is axiomatic and formulated in terms of geometric invariance with respect to the position of the observer. This is translated into mathematical terms, and the author develops the approach of Olver, Sapiro and Tannenbaum, which classifies all curve evolution equations. He then draws a complete parallel with another axiomatic approach using level-set methods: this leads to generalized curvature motions. Finally, novel, and very accurate, numerical schemes are proposed allowing one to compute the solution of highly degenerate evolution equations in a completely invariant way. The convergence of this scheme is also proved.

This volume collects the papers accepted for presentation at the Second European Conference on Computer Vision, held in Santa Margherita Ligure, Italy, May 19-22, 1992. Sixteen long papers, 41 short papers and 48 posters were selected from 308 submissions. The contributions are structured into 14 sections reflecting the major research topics in computer vision currently investigated worldwide. The sections are entitled: features, color, calibration and matching, depth, stereo-motion, tracking, active vision, binocular heads, curved surfaces and objects, reconstruction and shape, recognition, and applications.

Moments as projections of an image’s intensity onto a proper polynomial basis can be applied to many different aspects of image processing. These include invariant pattern recognition, image normalization, image registration, focus/ defocus measurement, and watermarking. This book presents a survey of both recent and traditional image analysis and pattern recognition methods, based on image moments, and offers new concepts of invariants to linear filtering and implicit invariants. In addition to the theory, attention is paid to efficient algorithms for moment computation in a discrete domain, and to computational aspects of orthogonal moments. The authors also illustrate the theory through practical examples, demonstrating moment invariants in real applications across computer vision, remote sensing and medical imaging. Key features: Presents a systematic review of the basic definitions and properties of moments covering geometric moments and complex moments. Considers invariants to traditional transforms – translation, rotation, scaling, and affine transform - from a new point of view, which offers new possibilities of designing optimal sets of invariants. Reviews and extends a recent field of invariants with respect to convolution/blurring. Introduces implicit moment invariants as a tool for recognizing elastically deformed objects. Compares various classes of orthogonal moments (Legendre, Zernike, Fourier-Mellin, Chebyshev, among others) and demonstrates their application to image reconstruction from moments. Offers comprehensive advice on the construction of various invariants illustrated with practical examples. Includes an accompanying website providing efficient numerical algorithms for moment computation and for constructing invariants of various kinds, with about 250 slides suitable for a graduate university course. Moments and Moment Invariants in Pattern Recognition is ideal for researchers and engineers involved in pattern recognition in medical imaging, remote sensing, robotics and computer vision. Post graduate students in image processing and pattern recognition will also find the book of interest.

Computer vision has been successful in several important applications recently. Vision techniques can now be used to build very good models of buildings from pictures quickly and easily, to overlay operation planning data on a neuros- geon’s view of a patient, and to recognise some of the gestures a user makes to a computer. Object recognition remains a very di cult problem, however. The key questions to understand in recognition seem to be: (1) how objects should be represented and (2) how to manage the line of reasoning that stretches from image data to object identity. An important part of the process of recognition { perhaps, almost all of it { involves assembling bits of image information into helpful groups. There is a wide variety of possible criteria by which these groups could be established { a set of edge points that has a symmetry could be one useful group; others might be a collection of pixels shaded in a particular way, or a set of pixels with coherent colour or texture. Discussing this process of grouping requires a detailed understanding of the relationship between what is seen in the image and what is actually out there in the world.