Cluster merging based on weighted Mahalanobis distance with application in digital mammography
A new clustering algorithm that uses a weighted Mahalanobis 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 M...
| Main Authors: | , , , , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English |
| Published: |
IEEE
1998
|
| Subjects: | |
| Online Access: | http://eprints.um.edu.my/8810/1/Cluster_merging_based_on_weighted_Mahalanobis_distance_with_application_in_digital_mammography.pdf |
| _version_ | 1825719599201517568 |
|---|---|
| author | Younis, K. Karim, M. Hardie, R. Loomis, J. Rogers, S. DeSimio, M. |
| author_facet | Younis, K. Karim, M. Hardie, R. Loomis, J. Rogers, S. DeSimio, M. |
| author_sort | Younis, K. |
| collection | UM |
| description | A new clustering algorithm that uses a weighted Mahalanobis 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. |
| first_indexed | 2024-03-06T05:22:12Z |
| format | Conference or Workshop Item |
| id | um.eprints-8810 |
| institution | Universiti Malaya |
| language | English |
| last_indexed | 2024-03-06T05:22:12Z |
| publishDate | 1998 |
| publisher | IEEE |
| record_format | dspace |
| spelling | um.eprints-88102014-03-25T07:03:26Z http://eprints.um.edu.my/8810/ Cluster merging based on weighted Mahalanobis distance with application in digital mammography Younis, K. Karim, M. Hardie, R. Loomis, J. Rogers, S. DeSimio, M. TA Engineering (General). Civil engineering (General) A new clustering algorithm that uses a weighted Mahalanobis 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. IEEE 1998 Conference or Workshop Item PeerReviewed application/pdf en http://eprints.um.edu.my/8810/1/Cluster_merging_based_on_weighted_Mahalanobis_distance_with_application_in_digital_mammography.pdf Younis, K. and Karim, M. and Hardie, R. and Loomis, J. and Rogers, S. and DeSimio, M. (1998) Cluster merging based on weighted Mahalanobis distance with application in digital mammography. In: Proceedings of the 1998 IEEE National Aerospace and Electronics Conference, NAECON, 1998, Dayton, OH, USA. http://www.scopus.com/inward/record.url?eid=2-s2.0-0032306128&partnerID=40&md5=abd392ca5b0b1c59a4f056f67ba795c1 http://ieeexplore.ieee.org/xpls/absall.jsp?arnumber=710194&tag=1 |
| spellingShingle | TA Engineering (General). Civil engineering (General) Younis, K. Karim, M. Hardie, R. Loomis, J. Rogers, S. DeSimio, M. Cluster merging based on weighted Mahalanobis distance with application in digital mammography |
| title | Cluster merging based on weighted Mahalanobis distance with application in digital mammography |
| title_full | Cluster merging based on weighted Mahalanobis distance with application in digital mammography |
| title_fullStr | Cluster merging based on weighted Mahalanobis distance with application in digital mammography |
| title_full_unstemmed | Cluster merging based on weighted Mahalanobis distance with application in digital mammography |
| title_short | Cluster merging based on weighted Mahalanobis distance with application in digital mammography |
| title_sort | cluster merging based on weighted mahalanobis distance with application in digital mammography |
| topic | TA Engineering (General). Civil engineering (General) |
| url | http://eprints.um.edu.my/8810/1/Cluster_merging_based_on_weighted_Mahalanobis_distance_with_application_in_digital_mammography.pdf |
| work_keys_str_mv | AT younisk clustermergingbasedonweightedmahalanobisdistancewithapplicationindigitalmammography AT karimm clustermergingbasedonweightedmahalanobisdistancewithapplicationindigitalmammography AT hardier clustermergingbasedonweightedmahalanobisdistancewithapplicationindigitalmammography AT loomisj clustermergingbasedonweightedmahalanobisdistancewithapplicationindigitalmammography AT rogerss clustermergingbasedonweightedmahalanobisdistancewithapplicationindigitalmammography AT desimiom clustermergingbasedonweightedmahalanobisdistancewithapplicationindigitalmammography |