Coarse-to-Fine object recognition using shock graphs

Authors:
Aurelie Bataille;Sven Dickinson
Affiliations:
University of Toronto;University of Toronto
Venue:
GbRPR'05 Proceedings of the 5th IAPR international conference on Graph-Based Representations in Pattern Recognition
Year:
2005

Citing 7
Cited 0

Matching Hierarchical Structures Using Association Graphs

ECCV '98 Proceedings of the 5th European Conference on Computer Vision-Volume II - Volume II
Inexact Multisubgraph Matching Using Graph Eigenspace and Clustering Models

Proceedings of the Joint IAPR International Workshop on Structural, Syntactic, and Statistical Pattern Recognition
Generic Model Abstraction from Examples

Revised Papers from the International Workshop on Sensor Based Intelligent Robots
Robust analysis of feature spaces: color image segmentation

CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
A shock grammar for recognition

CVPR '96 Proceedings of the 1996 Conference on Computer Vision and Pattern Recognition (CVPR '96)
View-Based 3-D Object Recognition using Shock Graphs

ICPR '02 Proceedings of the 16 th International Conference on Pattern Recognition (ICPR'02) Volume 3 - Volume 3
Shock Graphs and Shape Matching

ICCV '98 Proceedings of the Sixth International Conference on Computer Vision

Quantified Score

Hi-index	0.00

Visualization

Abstract

Shock graphs have emerged as a powerful generic 2-D shape representation. However, most approaches typically assume that the silhouette has been correctly segmented. In this paper, we present a framework for shock graph-based object recognition in less contrived scenes. The approach consists of two steps, beginning with the construction of a region adjacency graph pyramid. For a given region, we traverse this scale-space, using a model shock graph hypothesis to guide a region grouping process that strengthens the hypothesis. The result represents the best subset of regions, spanning different scales, that matches a given object model. In the second step, the correspondence between the region and model shock graphs is used to initialize an active skeleton that includes a shock graph-based energy term. This allows the skeleton to adapt to the image data while still adhering to a qualitative shape model. Together, the two components provide a coarse-to-fine, model-based segmentation/recognition framework.