@article{Jain:1999:DCR:331499.331504, abstract = {Clustering is the unsupervised classification of patterns (observations, data items, or feature vectors) into groups (clusters). The clustering problem has been addressed in many contexts and by researchers in many disciplines; this reflects its broad appeal and usefulness as one of the steps in exploratory data analysis. However, clustering is a difficult problem combinatorially, and differences in assumptions and contexts in different communities has made the transfer of useful generic concepts and methodologies slow to occur. This paper presents an overviewof pattern clustering methods from a statistical pattern recognition perspective, with a goal of providing useful advice and references to fundamental concepts accessible to the broad community of clustering practitioners. We present a taxonomy of clustering techniques, and identify cross-cutting themes and recent advances. We also describe some important applications of clustering algorithms such as image segmentation, object recognition, and information retrieval.}, acmid = {331504}, address = {New York, NY, USA}, author = {Jain, A. K. and Murty, M. N. and Flynn, P. J.}, doi = {10.1145/331499.331504}, hans = {otto}, interhash = {5113b61d428d4de4423182e5f2b2f468}, intrahash = {bd7234f7139a1651acfaed57b5c2551f}, issn = {0360-0300}, issue_date = {Sept. 1999}, journal = {ACM Comput. Surv.}, month = sep, number = 3, numpages = {60}, pages = {264--323}, publisher = {ACM}, title = {Data Clustering: A Review}, url = {http://doi.acm.org/10.1145/331499.331504}, volume = 31, year = 1999 } @article{Jain:1999:DCR:331499.331504, acmid = {331504}, address = {New York, NY, USA}, author = {Jain, A. K. and Murty, M. N. and Flynn, P. J.}, doi = {10.1145/331499.331504}, interhash = {5113b61d428d4de4423182e5f2b2f468}, intrahash = {b19bcef82a04eb82ee4abde53ee7d1c2}, issn = {0360-0300}, issue_date = {Sept. 1999}, journal = {ACM Comput. Surv.}, month = sep, number = 3, numpages = {60}, pages = {264--323}, publisher = {ACM}, title = {Data clustering: a review}, url = {http://doi.acm.org/10.1145/331499.331504}, volume = 31, year = 1999 } @article{Jain:1999:DCR:331499.331504, acmid = {331504}, address = {New York, NY, USA}, author = {Jain, A. K. and Murty, M. N. and Flynn, P. J.}, doi = {10.1145/331499.331504}, interhash = {5113b61d428d4de4423182e5f2b2f468}, intrahash = {66c50650bf611d5fa9027c839ab788fd}, issn = {0360-0300}, issue = {3}, issue_date = {Sept. 1999}, journal = {ACM Comput. Surv.}, month = {September}, numpages = {60}, pages = {264--323}, publisher = {ACM}, title = {Data clustering: a review}, url = {http://doi.acm.org/10.1145/331499.331504}, volume = 31, year = 1999 } @article{331504, abstract = {Clustering is the unsupervised classification of patterns (observations, data items, or feature vectors) into groups (clusters). The clustering problem has been addressed in many contexts and by researchers in many disciplines; this reflects its broad appeal and usefulness as one of the steps in exploratory data analysis. However, clustering is a difficult problem combinatorially, and differences in assumptions and contexts in different communities has made the transfer of useful generic concepts and methodologies slow to occur. This paper presents an overview of pattern clustering methods from a statistical pattern recognition perspective, with a goal of providing useful advice and references to fundamental concepts accessible to the broad community of clustering practitioners. We present a taxonomy of clustering techniques, and identify cross-cutting themes and recent advances. We also describe some important applications of clustering algorithms such as image segmentation, object recognition, and information retrieval.}, address = {New York, NY, USA}, author = {Jain, A. K. and Murty, M. N. and Flynn, P. J.}, doi = {http://doi.acm.org/10.1145/331499.331504}, interhash = {5113b61d428d4de4423182e5f2b2f468}, intrahash = {b19bcef82a04eb82ee4abde53ee7d1c2}, issn = {0360-0300}, journal = {ACM Comput. Surv.}, number = 3, pages = {264--323}, publisher = {ACM}, title = {Data clustering: a review}, url = {http://portal.acm.org/citation.cfm?id=331499.331504&coll=Portal&dl=ACM&CFID=26215063&CFTOKEN=18848029}, volume = 31, year = 1999 }