A robust clustering algorithm based on competitive agglomeration and soft rejection of outliers

We present a new clustering algorithm that addresses two major issues associated with conventional partitional clustering: the difficulty in determining the number of clusters, and the sensitivity to noise and outliers. The proposed algorithm determines the number of clusters by a process of competi...

Full description

Saved in:
Bibliographic Details
Published in:PROC IEEE COMPUT SOC CONF COMPUT VISION PATTERN RECOGNIT pp. 550 - 555
Main Authors: Frigui, H., Krishnapuram, R.
Format: Conference Proceeding Journal Article
Language:English
Published: IEEE 1996
Subjects:
Clustering algorithms
Computer science
Data mining
Electric breakdown
Noise robustness
Partitioning algorithms
Prototypes
Shape measurement
Size measurement
Statistics
ISBN:9780818672590, 0818672595
ISSN:1063-6919, 1063-6919
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We present a new clustering algorithm that addresses two major issues associated with conventional partitional clustering: the difficulty in determining the number of clusters, and the sensitivity to noise and outliers. The proposed algorithm determines the number of clusters by a process of competitive agglomeration. Noise immunity is achieved by integrating concepts from robust statistics into the algorithm. The proposed approach can incorporate different distance measures in the objective function to find an unknown number of clusters of various types including lines, planes and surfaces.
Bibliography:SourceType-Scholarly Journals-2
ObjectType-Feature-2
ObjectType-Conference Paper-1
content type line 23
SourceType-Conference Papers & Proceedings-1
ObjectType-Article-3
ISBN:9780818672590
0818672595
ISSN:1063-6919
1063-6919
DOI:10.1109/CVPR.1996.517126