Readings in Computer Vision

The field of computer vision combines techniques from physics, mathematics, psychology, artificial intelligence, and computer science to examine how machines might construct meaningful descriptions of their surrounding environment. The editors of this volume, prominent researchers and leaders of the SRI International AI Center Perception Group, have selected sixty papers, most published since 1980, with the viewpoint that computer vision is concerned with solving seven basic problems:

• Reconstructing 3D scenes from 2D images
• Decomposing images into their component parts
• Recognizing and assigning labels to scene objects
• Deducing and describing relations among scene objects
• Determining the nature of computer architectures that can support the visual function
• Representing abstractions in the world of computer memory
• Matching stored descriptions to image representation

Each chapter of this volume addresses one of these problems through an introductory discussion, which identifies major ideas and summarizes approaches, and through reprints of key research papers. Two appendices on crucial assumptions in image interpretation and on parallel architectures for vision applications, a glossary of technical terms, and a comprehensive bibliography and index complete the volume.

Acknowledgments
Introduction
Image Analysis: Problems, Progress and Prospects, A.Rosenfeld
CHAPTER 1: RECOVERING SCENE GEOMETRY
A Stochastic Approach to Stereo Vision, S.Barnard
Epipolar-Plane Image Analysis: A Technique for Analyzing Motion Sequences, R.Bolles & H.Baker
Preface--The Changing Shape of Computer Vision, M.Brady
Understanding Image Intensities, B.Horn
A Computer Algorithm for Reconstructing a Scene from Two Projections, H.Longuet-Higgins
Practical Real-Time Imaging Stereo Matcher, H.Nishihara
Detection of Binocular Disparities, K.Prazdny
Hierarchical Warp Stereo, L.Quam
Stereo Integral Equation, G.Smith
Recovering the Camera Parameters from a Transformation Matrix, T.Strat
One-Eyed Stereo: A General Approach to Modeling 3-D Scene Geometry, T.Strat and M.Fischler
An Algebraic Approach to Shape-fromImage Problems, K.Sugihara
Analysis of Visual Motion by Biological and Computer Systems, S.Ullman
An Image Flow Paradigm, A.M.Waxman

CHAPTER 2: IMAGE PARTITIONING AND PERCEPTUAL ORGANIZATION
Extracting Straight Lines, J.Burns, A.Hanson, & E.Riseman
A Computational Approach to Edge Detection, J.Canny
Linear Delineation, M.Fischler & H.Wolf
Perceptual Organization and Curve Partitioning, M.Fischler & R.Bolles
Digital Stereo Edges from Zero Crossing of Second Directional Derivatives, R.Haralick
Parts of Recognition, D.Hoffman & W.Richards
Textons, The Fundamental Elements in Preattentive Vision and Perception of Textures, B.Julesz & J.Bergen
Mapping Image Properties into Shape Constraints: Skewed Symmetry, Affine-Transformable Patterns, and the Shape-from-Texture Paradigm, T.Kanade & J.Kender
Analyzing Oriented Patterns, M.Kass & A.Witkin
Capturing the Local Structure of Image Discontinuities in Two Dimensions, Y.Leclerc
Segmentation and Aggregation: An Approach to Figure-Ground Phenomena, D.Lowe & T.Binford
Color Constancy: A Method for Recovering Surface Spectral Reflectance, L.Maloney & B.Wandell
Visual Routines, S.Ullman
Scale-Space Filtering, A.Witkin
Early Orientation Selection: Tangent Fields and the Dimensionality of Their Support, S.Zucker

CHAPTER 3: RECOGNITION AND LABELING OF SCENE OBJECTS
3DPO: A Three-Dimensional Part Orientation System, R.Bolles, P.Howard, & M.Hannah
Model-Based Three-Dimensional Interpretations of TwoDimensional Images, R.Brooks
Special Purpose Automatic Programming for 3D Model-Based Vision, Chris Goad
Model-Based Recognition and Localization from Sparse Range or Tactile Data, W.Eric, L.Grimson, & T.Lozano-Perez
Rule-Based Interpretation of Aerial Imagery, D.McKeown,Jr., W.Harvey,Jr., & J.McDermott

CHAPTER 4: RELATIONAL DESCRIPTION
Visual Map Making for a Mobile Robot, R.Brooks
A Heuristic Program to Solve Geometric-Analogy Problems, T.Evans
Problem-Solving with Diagrammatic Representations, B.Funt
The 3D MOSAIC Scene Understanding System: Incremental Reconstruction of 3D Scenes for Complex Images, M.Herman & T.Kanade
Terrain Models for an Autonomous Land Vehicle, D.Lawton, T.Levitt, C.McConnell, & J.Glicksman
Experiments in Using a Theorem Prover to Prove and Develop Geometrical Theorems in Computer Vision, M.Swain & J.Mundy
Knowledge Organization and Its Role in Representation and Interpretation for Time-Varying Data: The ALVEN System, J.Tsotsos

CHAPTER 5: VISION SYSTEM ARCHITECTURES AND COMPUTATIONAL PARADIGMS
A Learning Algorithm for Boltzmann Machines, D.Ackley, G.Hinton, & T.Sejnowski
Parameter Nets, D.Ballard
Image Processing by Simulated Annealing, P.Carnevali, L.Coletti, & S.Patarnello
Preface to S.Geman and D.Geman, "Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images," G.Smith
Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images, S.Geman & D.Geman
On the Foundations of Relaxation Labeling Processes, R.Hummel & S.Zucker
Optimization by Simulated Annealing, S.Kirkpatrick, C.Gelatt,Jr., & M.Vecchi
Visual Information Processing: Artificial Intelligence and the Sensorium of Sight, D.Marr & H.Nishihara
Computational Vision and Regularization Theory, T.Poggio, V.Torre, & C.Koch

CHAPTER 6: REPRESENTATIONS AND TRANSFORMATIONS
Geometry for Construction and Display, D.Ahuja & S.Coons
Global and Local Deformations of Solid Primitives, A.Barr
The Laplacian Pyramid as a Compact Image Code, P.Burt & E.Adelson
Perceptual Organization and the Representation of Natural Form, A.Pentland
Codon Constraints on Closed 2D Shapes, W.Richards & D.Hoffman

CHAPTER 7: MATCHING, MODEL FITTING, DEDUCTION, AND INFORMATION INTEGRATION
Generalizing the Hough Transform to Detect Arbitrary Shapes, D.Ballard
Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography, M.Fischler & R.Bolles
Detection of Roads and Linear Structures in Low-Resolution Aerial Imagery Using a Multisource Knowledge Integration Technique, M.Fischler, J.Tenenbaum, & H.Wolf
Representations Based on Zero-crossings in Scale-Space, R.Hummel
Signal Matching Through Scale Space, A.Witkin, D.Terzopoulis, & M.Kass

APPENDIX A: KEY IDEAS, ASSUMPTIONS, AND OPEN ISSUES IN COMPUTER VISION
APPENDIX B: PARALLEL COMPUTER ARCHITECTURES FOR COMPUTER VISION
Glossary
Bibliography
Index