Shape, Contour and Grouping in Computer Vision

1. Front Matter

   Pages I-VIII

   PDF

2. Introduction

   1. Introduction

      • David Forsyth, Joe Mundy

      Pages 3-8

   2. An Empirical-Statistical Agenda for Recognition

      • David Forsyth

      Pages 9-21

   3. A Formal-Physical Agenda for Recognition

      • Joe Mundy

      Pages 22-27

3. Shape

   1. Shape Models and Object Recognition

      • Jean Ponce, Martha Cepeda, Sung-il Pae, Steve Sullivan

      Pages 31-57

   2. Order Structure, Correspondence, and Shape Based Categories

      • Stefan Carlsson

      Pages 58-71

   3. Quasi-Invariant Parameterisations and Their Applications in Computer Vision

      • Jun Sato, Roberto Cipolla

      Pages 72-92

4. Shading

   1. Representations for Recognition Under Variable Illumination

      • David Juris Kriegman, Peter N. Belhumeur, Athinodoros S. Georghiades

      Pages 95-131

   2. Shadows, Shading, and Projective Ambiguity

      • Peter N. Belhumeur, David Juris Kriegman, Alan L. Yuille

      Pages 132-151

5. Grouping

   1. Grouping in the Normalized Cut Framework

      • Jitendra Malik, Jianbo Shi, Serge Belongie, Thomas Leung

      Pages 155-164

   2. Geometric Grouping of Repeated Elements within Images

      • Frederik Schaffalitzky, Andrew Zisserman

      Pages 165-181

   3. Constrained Symmetry for Change Detection

      • Rupert W. Curwen, Joe L. Mundy

      Pages 182-195

   4. Grouping Based on Coupled Diffusion Maps

      • Marc Proesmans, Luc Van Gool

      Pages 196-213

6. Representation and Recognition

   1. Integrating Geometric and Photometric Information for Image Retrieval

      • Cordelia Schmid, Roger Mohr, Andrew Zisserman

      Pages 217-233

   2. Towards the Integration of Geometric and Appearance-Based Object Recognition

      • Joe Mundy, Tushar Saxena

      Pages 234-245

   3. Recognizing Objects Using Color-Annotated Adjacency Graphs

      • Peter Tu, Richard Hartley, Tushar Saxena

      Pages 246-263

   4. A Cooperating Strategy for Objects Recognition

      • Antonio Chella, Vito Di Gesù, Ignazio Infantino, Daniela Intravaia, Cesare Valenti

      Pages 264-274

7. Statistics, Learning and Recognition

   1. Model Selection for Two View Geometry:A Review

      • Philip H. S. Torr

      Pages 277-301

   2. Finding Objects by Grouping Primitives

      • David Forsyth, John Haddon, Sergey Ioffe

      Pages 302-318

   3. Object Recognition with Gradient-Based Learning

      • Yann LeCun, Patrick Haffner, Léon Bottou, Yoshua Bengio

      Pages 319-345

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.

• Computer Vision
• Image Processing
• Machine Learning
• Object Representation
• Pattern Recognition
• Shading
• cognition
• learning
• object recognition

• Computer Science Division, University of California at Berkeley, Berkeley, USA

  David A. Forsyth

• G.E. Corporate Research and Development, Niskayuna, USA

  Joseph L. Mundy

• Palermo University, C.I.T.C., Sicily, Italy

  Vito Gesú

• Department of Engineering, University of Cambridge, Cambridge, UK

  Roberto Cipolla

Policies and ethics