Visual alphabets on different levels of abstraction for the recognition of deformable objects

Authors:
Martin Stommel;Klaus-Dieter Kuhnert
Affiliations:
TZI Center for Computing and Communication Technologies, University Bremen, Bremen, Germany;Institute of Real-Time Learning Systems, University of Siegen, Siegen, Germany
Venue:
SSPR&SPR'10 Proceedings of the 2010 joint IAPR international conference on Structural, syntactic, and statistical pattern recognition
Year:
2010

Citing 8
Cited 1

Unsupervised Learning of Models for Recognition

ECCV '00 Proceedings of the 6th European Conference on Computer Vision-Part I
Object Recognition from Local Scale-Invariant Features

ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
Spatial Priors for Part-Based Recognition Using Statistical Models

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Bottom-up/Top-Down Image Parsing by Attribute Graph Grammar

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
Local Features for Object Class Recognition

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
Multiple Object Class Detection with a Generative Model

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
An Inexact Graph Comparison Approach in Joint Eigenspace

SSPR & SPR '08 Proceedings of the 2008 Joint IAPR International Workshop on Structural, Syntactic, and Statistical Pattern Recognition
A Hierarchical Model for the Recognition of Deformable Objects

ICCVG 2008 Proceedings of the International Conference on Computer Vision and Graphics: Revised Papers

Classification of semantic concepts to support the analysis of the inter-cultural visual repertoires of TV news reviews

KI'11 Proceedings of the 34th Annual German conference on Advances in artificial intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

Recognition systems for complex and deformable objects must handle a variety of possible object appearances. In this paper, a compositional approach to this problem is studied which splits the set of possible appearances into easier sub-problems. To this end, a grammar is introduced that represents objects by a hierarchy of increasingly abstract visual alphabets. These alphabets store features, complex patterns and different views of objects. The geometrical constraints are optimised to the respective level of abstraction. The performance of the method is demonstrated on a cartoon data base with high intra-class variance.