Image Processing and Analysis with Graphs

14

The Role of Graphs in Matching Shapes and in Categorization

Benjamin Kimia

Brown University

School of Engineering

Providence, Rhode Island, USA

[e-mail]

CONTENTS

14.1  Introduction

14.2  Using Shock Graphs for Shape Matching

14.3  Using Proximity Graphs for Categorization

14.3.1  Indexing: Euclidean versus Metric Spaces

14.3.2  Metric-based Indexing Methods

14.3.3  Capturing the Local Topology

14.4  Conclusion

14.5  Acknowledgment

Bibliography

14.1  Introduction

This chapter explores the value of graphs in computer vision from the perspective of representing both structural quantum variations as well as metric changes, as applied to the matching and categorization problems. It briefly overviews our particular approach in using ...