View-tuned approximate partial matching kernel from hierarchical growing neural gases

Authors:
Marco Kortkamp;Sven Wachsmuth
Affiliations:
Applied Informatics, Faculty of Technology, Bielefeld, Germany;Applied Informatics, Faculty of Technology, Bielefeld, Germany and Central Lab Facilities, CITEC, Bielefeld, Germany
Venue:
ICANN'11 Proceedings of the 21st international conference on Artificial neural networks - Volume Part II
Year:
2011

Citing 8
Cited 0

Kernel Methods for Pattern Analysis

Kernel Methods for Pattern Analysis
Pictorial Structures for Object Recognition

International Journal of Computer Vision
Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories

CVPRW '04 Proceedings of the 2004 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'04) Volume 12 - Volume 12
A Sparse Object Category Model for Efficient Learning and Exhaustive Recognition

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Continuous visual codebooks with a limited branching tree growing neural gas

ICANN'10 Proceedings of the 20th international conference on Artificial neural networks: Part III
SURF: speeded up robust features

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part I
Building kernels from binary strings for image matching

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.02

Visualization

Abstract

The problem of comparing images or image regions can be considered as the problem of matching unordered sets of high dimensional visual features. We show that an hierarchical Growing Neural Gas (GNG) can robustly be used to approximate the optimal partial matching cost between vector sets. Further, we extend the unordered set matching, such that the matching of local features pays attention to the structure of the object and the relative positions of the parts. This view-tuning is also realized with hierarchical GNGs and yields an efficient Mercer Kernel.