DocumentCode :
1499782
Title :
A modified version of the K-means algorithm with a distance based on cluster symmetry
Author :
Su, Mu-Chun ; Chou, Chien-Hsing
Author_Institution :
Dept. of Comput. Sci. & Inf. Eng., Nat. Central Univ., Chung-Li, Taiwan
Volume :
23
Issue :
6
fYear :
2001
fDate :
6/1/2001 12:00:00 AM
Firstpage :
674
Lastpage :
680
Abstract :
We propose a modified version of the K-means algorithm to cluster data. The proposed algorithm adopts a novel nonmetric distance measure based on the idea of “point symmetry”. This kind of “point symmetry distance” can be applied in data clustering and human face detection. Several data sets are used to illustrate its effectiveness
Keywords :
computer vision; data handling; face recognition; pattern clustering; K-means algorithm; cluster symmetry; data clustering; human face recognition; nonmetric distance measure; pattern recognition; point symmetry distance; Algorithm design and analysis; Clustering algorithms; Covariance matrix; Engineering in medicine and biology; Euclidean distance; Face detection; Humans; Image analysis; Pattern analysis; Pattern recognition;
fLanguage :
English
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
Publisher :
ieee
ISSN :
0162-8828
Type :
jour
DOI :
10.1109/34.927466
Filename :
927466
Link To Document :
بازگشت