Clustering Using Normalized Path-Based Metric

Authors:
Jundi Ding;Runing Ma;Songcan Chen;Jingyu Yang
Affiliations:
School of Comp. Sci. & Tech., Nanjing University of Science and Technology, Nanjing, China and Department of Computer Science & Engineering, Nanjing University of Aeronautics & Astronautics, Nanji ...;Department of Mathematics, Nanjing University of Aeronautics & Astronautics, Nanjing, China;Department of Computer Science & Engineering, Nanjing University of Aeronautics & Astronautics, Nanjing, China;School of Comp. Sci. & Tech., Nanjing University of Science and Technology, Nanjing, China
Venue:
ISNN '08 Proceedings of the 5th international symposium on Neural Networks: Advances in Neural Networks, Part II
Year:
2008

Citing 11
Cited 0

Normalized Cuts and Image Segmentation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Path Based Pairwise Data Clustering with Application to Texture Segmentation

EMMCVPR '01 Proceedings of the Third International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition
Path-Based Clustering for Grouping of Smooth Curves and Texture Segmentation

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Model-Based Distance for Clustering

IJCNN '00 Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN'00)-Volume 4 - Volume 4
Spectral Grouping Using the Nyström Method

IEEE Transactions on Pattern Analysis and Machine Intelligence
Efficient Graph-Based Image Segmentation

International Journal of Computer Vision
Robust Path-Based Spectral Clustering with Application to Image Segmentation

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
The Bottleneck Geodesic: Computing Pixel Affinity

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
A fast directed tree based neighborhood clustering algorithm for image segmentation

ICONIP'06 Proceedings of the 13th international conference on Neural Information Processing - Volume Part II
A neighborhood-based clustering algorithm

PAKDD'05 Proceedings of the 9th Pacific-Asia conference on Advances in Knowledge Discovery and Data Mining
Image specific feature similarities

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we propose a normalized path-based metric based on an introduced neighborhood density index which can sufficiently exploit the local density "revealed" by data. The metric axioms (positive definite property, symmetry and triangular inequality) are strictly proved in theory. Using this idea of path, we further devise a heuristic clustering algorithm which can perform the elongated structure extraction, uneven lighting background isolation, grains of tiny objects segmentation and figure-ground separation. In particular, when the pairwise distances between data are given, the proposed algorithm has a computational complexity linear in the size of data. Extensive experiments are conducted to validate its effectiveness, efficiency and competitiveness in resistance to noise.