Shape, Contour and Grouping in Computer Vision

✍ Scribed by David A. Forsyth, Joseph L. Mundy, Vito di Gesú, Roberto Cipolla (auth.)

• Publisher: Springer-Verlag Berlin Heidelberg
• Year: 1999
• Tongue: English
• Leaves: 339
• Series: Lecture Notes in Computer Science 1681
• Edition: 1
• Category: Library

✦ Synopsis

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.

✦ Table of Contents

Introduction....Pages 3-8
An Empirical-Statistical Agenda for Recognition....Pages 9-21
A Formal-Physical Agenda for Recognition....Pages 22-27
Shape Models and Object Recognition....Pages 31-57
Order Structure, Correspondence, and Shape Based Categories....Pages 58-71
Quasi-Invariant Parameterisations and Their Applications in Computer Vision....Pages 72-92
Representations for Recognition Under Variable Illumination....Pages 95-131
Shadows, Shading, and Projective Ambiguity....Pages 132-151
Grouping in the Normalized Cut Framework....Pages 155-164
Geometric Grouping of Repeated Elements within Images....Pages 165-181
Constrained Symmetry for Change Detection....Pages 182-195
Grouping Based on Coupled Diffusion Maps....Pages 196-213
Integrating Geometric and Photometric Information for Image Retrieval....Pages 217-233
Towards the Integration of Geometric and Appearance-Based Object Recognition....Pages 234-245
Recognizing Objects Using Color-Annotated Adjacency Graphs....Pages 246-263
A Cooperating Strategy for Objects Recognition....Pages 264-274
Model Selection for Two View Geometry:A Review....Pages 277-301
Finding Objects by Grouping Primitives....Pages 302-318
Object Recognition with Gradient-Based Learning....Pages 319-345

✦ Subjects

Image Processing and Computer Vision; Pattern Recognition; Computer Graphics; Artificial Intelligence (incl. Robotics)