This Article 
 Bibliographic References 
 Add to: 
Threshold Validity for Mutual Neighborhood Clustering
January 1993 (vol. 15 no. 1)
pp. 89-92

Clustering algorithms have the annoying characteristic of finding clusters in random data. A theoretical analysis of the threshold of the mutual neighborhood clustering algorithm (MNCA) under the hypothesis of random data is presented. This yields a theoretical minimum value of this threshold below which even unclustered data are broken into separate clusters. To derive the threshold, a theorem about mutual near neighbors in a Poisson process is stated and proved. Simple experiments demonstrate the usefulness of the theoretical thresholds.

[1] K. C. Gowda and G. Krishna, "Disaggregative clustering using the concept of mutual nearest neighborhood,"IEEE Trans. Syst. Man Cybern., vol. SMC-8, no. 12, pp. 888-895, Dec. 1978.
[2] A. K. Jain and R. C. Dubes,Algorithms for Clustering Data. Englewood Cliffs, NJ: Prentice-Hall, 1988.
[3] R. A. Jarvis and E. A. Patrick, "Clustering using a similarity measure based on shared near neighbors,"IEEE Trans. Comput., vol. C-22, pp. 1025-1034, 1973.
[4] R. F. Ling and G. G. Killough, "Probability tables for cluster analysis based on a theory of random graphs,"J. Amer. Stat. Assoc., vol. 71, no. 354, pp. 293-300, June 1976.
[5] S. P. Smith and A. K. Jain, "Testing for uniformity in multidimensional data,"IEEE Trans. Patt. Anal. Machine Intell., vol. PAMI-6, no. 1, pp. 73-81, Jan. 1984.

Index Terms:
threshold validity; image recognition; mutual neighborhood clustering; random data; Poisson process; image recognition; random processes
S.P. Smith, "Threshold Validity for Mutual Neighborhood Clustering," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 15, no. 1, pp. 89-92, Jan. 1993, doi:10.1109/34.184777
Usage of this product signifies your acceptance of the Terms of Use.