Mode seeking clustering by KNN and mean shift evaluated

R.P.W. Duin; A.L.N. Fred; M. Loog; E. Pekalska

doi:10.1007/978-3-642-34166-3_6

Mode seeking clustering by KNN and mean shift evaluated

R.P.W. Duin, A.L.N. Fred, M. Loog, E. Pekalska

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

20 Citations (Scopus)

Abstract

Clustering by mode seeking is most popular using the mean shift algorithm. A less well known alternative with different properties on the computational complexity is kNN mode seeking, based on the nearest neighbor rule instead of the Parzen kernel density estimator. It is faster and allows for much higher dimensionalities. We compare the performances of both procedures using a number of labeled datasets. The retrieved clusters are compared with the given class labels. In addition, the properties of the procedures are investigated for prototype selection. It is shown that kNN mode seeking is well performing and is feasible for large scale problems with hundreds of dimensions and up to a hundred thousand data points. The mean shift algorithm may perform better than kNN mode seeking for smaller dataset sizes.

Original language	English
Title of host publication	Structural, Syntactic, and Statistical Pattern Recognition (Joint IAPR International Workshop, SSPR&SPR 2012, Hiroshima, Japan, November 7-9, 2012. Proceedings)
Editors	G. Gimel'farb, E. Hancock, A. Imiya, A. Kuijper, M. Kudo, S. Omachi, T. Windeatt, K. Yamada
Place of Publication	Berlin
Publisher	Springer
Pages	51-59
ISBN (Print)	978-3-642-34165-6
DOIs	https://doi.org/10.1007/978-3-642-34166-3_6
Publication status	Published - 2012
Externally published	Yes
Event	Joint IAPR International Workshop SSPR+SPR, Hiroshima, Japan, November 7-9, 2012 - Hiroshima, Japan Duration: 7 Nov 2012 → 9 Nov 2012

Publication series

Name	Lecture Notes in Computer Science
Volume	7626
ISSN (Print)	0302-9743

Conference

Conference	Joint IAPR International Workshop SSPR+SPR, Hiroshima, Japan, November 7-9, 2012
Country/Territory	Japan
City	Hiroshima
Period	7/11/12 → 9/11/12
Other	Joint IAPR International Workshop SSPR+SPR 2012

Access to Document

10.1007/978-3-642-34166-3_6

Cite this

Duin, R. P. W., Fred, A. L. N., Loog, M., & Pekalska, E. (2012). Mode seeking clustering by KNN and mean shift evaluated. In G. Gimel'farb, E. Hancock, A. Imiya, A. Kuijper, M. Kudo, S. Omachi, T. Windeatt, & K. Yamada (Eds.), Structural, Syntactic, and Statistical Pattern Recognition (Joint IAPR International Workshop, SSPR&SPR 2012, Hiroshima, Japan, November 7-9, 2012. Proceedings) (pp. 51-59). (Lecture Notes in Computer Science; Vol. 7626). Springer. https://doi.org/10.1007/978-3-642-34166-3_6

Duin, R.P.W. ; Fred, A.L.N. ; Loog, M. et al. / Mode seeking clustering by KNN and mean shift evaluated. Structural, Syntactic, and Statistical Pattern Recognition (Joint IAPR International Workshop, SSPR&SPR 2012, Hiroshima, Japan, November 7-9, 2012. Proceedings). editor / G. Gimel'farb ; E. Hancock ; A. Imiya ; A. Kuijper ; M. Kudo ; S. Omachi ; T. Windeatt ; K. Yamada. Berlin : Springer, 2012. pp. 51-59 (Lecture Notes in Computer Science).

@inproceedings{d2245995af2e46fbafc263d4c39d438c,

title = "Mode seeking clustering by KNN and mean shift evaluated",

abstract = "Clustering by mode seeking is most popular using the mean shift algorithm. A less well known alternative with different properties on the computational complexity is kNN mode seeking, based on the nearest neighbor rule instead of the Parzen kernel density estimator. It is faster and allows for much higher dimensionalities. We compare the performances of both procedures using a number of labeled datasets. The retrieved clusters are compared with the given class labels. In addition, the properties of the procedures are investigated for prototype selection. It is shown that kNN mode seeking is well performing and is feasible for large scale problems with hundreds of dimensions and up to a hundred thousand data points. The mean shift algorithm may perform better than kNN mode seeking for smaller dataset sizes.",

author = "R.P.W. Duin and A.L.N. Fred and M. Loog and E. Pekalska",

year = "2012",

doi = "10.1007/978-3-642-34166-3_6",

language = "English",

isbn = "978-3-642-34165-6",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "51--59",

editor = "G. Gimel'farb and E. Hancock and A. Imiya and A. Kuijper and M. Kudo and S. Omachi and T. Windeatt and K. Yamada",

booktitle = "Structural, Syntactic, and Statistical Pattern Recognition (Joint IAPR International Workshop, SSPR&SPR 2012, Hiroshima, Japan, November 7-9, 2012. Proceedings)",

note = "Joint IAPR International Workshop SSPR+SPR, Hiroshima, Japan, November 7-9, 2012<br/> ; Conference date: 07-11-2012 Through 09-11-2012",

}

Duin, RPW, Fred, ALN, Loog, M & Pekalska, E 2012, Mode seeking clustering by KNN and mean shift evaluated. in G Gimel'farb, E Hancock, A Imiya, A Kuijper, M Kudo, S Omachi, T Windeatt & K Yamada (eds), Structural, Syntactic, and Statistical Pattern Recognition (Joint IAPR International Workshop, SSPR&SPR 2012, Hiroshima, Japan, November 7-9, 2012. Proceedings). Lecture Notes in Computer Science, vol. 7626, Springer, Berlin, pp. 51-59, Joint IAPR International Workshop SSPR+SPR, Hiroshima, Japan, November 7-9, 2012
, Hiroshima, Japan, 7/11/12. https://doi.org/10.1007/978-3-642-34166-3_6

Mode seeking clustering by KNN and mean shift evaluated. / Duin, R.P.W.; Fred, A.L.N.; Loog, M. et al.
Structural, Syntactic, and Statistical Pattern Recognition (Joint IAPR International Workshop, SSPR&SPR 2012, Hiroshima, Japan, November 7-9, 2012. Proceedings). ed. / G. Gimel'farb; E. Hancock; A. Imiya; A. Kuijper; M. Kudo; S. Omachi; T. Windeatt; K. Yamada. Berlin: Springer, 2012. p. 51-59 (Lecture Notes in Computer Science; Vol. 7626).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Mode seeking clustering by KNN and mean shift evaluated

AU - Duin, R.P.W.

AU - Fred, A.L.N.

AU - Loog, M.

AU - Pekalska, E.

PY - 2012

Y1 - 2012

N2 - Clustering by mode seeking is most popular using the mean shift algorithm. A less well known alternative with different properties on the computational complexity is kNN mode seeking, based on the nearest neighbor rule instead of the Parzen kernel density estimator. It is faster and allows for much higher dimensionalities. We compare the performances of both procedures using a number of labeled datasets. The retrieved clusters are compared with the given class labels. In addition, the properties of the procedures are investigated for prototype selection. It is shown that kNN mode seeking is well performing and is feasible for large scale problems with hundreds of dimensions and up to a hundred thousand data points. The mean shift algorithm may perform better than kNN mode seeking for smaller dataset sizes.

AB - Clustering by mode seeking is most popular using the mean shift algorithm. A less well known alternative with different properties on the computational complexity is kNN mode seeking, based on the nearest neighbor rule instead of the Parzen kernel density estimator. It is faster and allows for much higher dimensionalities. We compare the performances of both procedures using a number of labeled datasets. The retrieved clusters are compared with the given class labels. In addition, the properties of the procedures are investigated for prototype selection. It is shown that kNN mode seeking is well performing and is feasible for large scale problems with hundreds of dimensions and up to a hundred thousand data points. The mean shift algorithm may perform better than kNN mode seeking for smaller dataset sizes.

U2 - 10.1007/978-3-642-34166-3_6

DO - 10.1007/978-3-642-34166-3_6

M3 - Conference contribution

SN - 978-3-642-34165-6

T3 - Lecture Notes in Computer Science

SP - 51

EP - 59

BT - Structural, Syntactic, and Statistical Pattern Recognition (Joint IAPR International Workshop, SSPR&SPR 2012, Hiroshima, Japan, November 7-9, 2012. Proceedings)

A2 - Gimel'farb, G.

A2 - Hancock, E.

A2 - Imiya, A.

A2 - Kuijper, A.

A2 - Kudo, M.

A2 - Omachi, S.

A2 - Windeatt, T.

A2 - Yamada, K.

PB - Springer

CY - Berlin

T2 - Joint IAPR International Workshop SSPR+SPR, Hiroshima, Japan, November 7-9, 2012<br/>

Y2 - 7 November 2012 through 9 November 2012

ER -

Duin RPW, Fred ALN, Loog M, Pekalska E. Mode seeking clustering by KNN and mean shift evaluated. In Gimel'farb G, Hancock E, Imiya A, Kuijper A, Kudo M, Omachi S, Windeatt T, Yamada K, editors, Structural, Syntactic, and Statistical Pattern Recognition (Joint IAPR International Workshop, SSPR&SPR 2012, Hiroshima, Japan, November 7-9, 2012. Proceedings). Berlin: Springer. 2012. p. 51-59. (Lecture Notes in Computer Science). doi: 10.1007/978-3-642-34166-3_6

Mode seeking clustering by KNN and mean shift evaluated

Abstract

Publication series

Conference

Access to Document

Fingerprint

Cite this