DocumentCode :
327554
Title :
Cluster merging based on weighted mahalanobis distance with application in digital mammograph
Author :
Younis, K. ; Karim, Mohammed ; Hardie, Russell ; Loomis, John ; Rogers, Steven ; DeSimio, Martin
Author_Institution :
Dayton Univ., OH, USA
fYear :
1998
fDate :
13-17 Jul 1998
Firstpage :
525
Lastpage :
530
Abstract :
A new clustering algorithm that uses a weighted Mahdlanobis distance as a distance metric to perform partitional clustering is proposed. The covariance matrices of the generated clusters are used to determine cluster similarity and closeness so that clusters which are similar in shape and close in Mahalanobis distance can be merged together serving the ultimate goal of automatically determining the optimal number of classes present in the data. Properties of the new algorithm are presented by examining the clustering quality for codebooks designed with the proposed method and another common method that uses Euclidean distance. The new algorithm provides better results than the competing method on a variety of data sets. Application of this algorithm to the problem of detecting suspicious regions in a mammogram is discussed
Keywords :
cancer; covariance matrices; image classification; mammography; medical image processing; pattern clustering; Cluster merging; Euclidean distance; cluster similarity; clustering algorithm; codebooks; covariance matrices; digital mammograph; distance metric; partitional clustering; weighted mahalanobis distance; Algorithm design and analysis; Books; Clustering algorithms; Euclidean distance; Iterative algorithms; Mammography; Merging; Partitioning algorithms; Pattern recognition; Shape;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Aerospace and Electronics Conference, 1998. NAECON 1998. Proceedings of the IEEE 1998 National
Conference_Location :
Dayton, OH
ISSN :
0547-3578
Print_ISBN :
0-7803-4449-9
Type :
conf
DOI :
10.1109/NAECON.1998.710194
Filename :
710194
Link To Document :
بازگشت