The Community for Technology Leaders
RSS Icon
Subscribe
Issue No.12 - December (1971 vol.20)
pp: 1521-1527
ABSTRACT
This paper discusses methods of estimating the probability of error for the Bayes' classifier which must be designed and tested with a finite number of classified samples. The expected difference between estimates is discussed. A simplifled algorithm to compute the leaving-one-out method is proposed for multivariate normal distributions wtih unequal co-variance matrices. The discussion is extended to nonparametric classifiers by using the Parzen approximation for the density functions. Experimental results are shown for both parametric and nonparametric cases.
INDEX TERMS
Bayes' classifier, estimation, finite number of samples, pattern recognition, probability of error.
CITATION
K. Fukunaga, D.L. Kessell, "Estimation of Classification Error", IEEE Transactions on Computers, vol.20, no. 12, pp. 1521-1527, December 1971, doi:10.1109/T-C.1971.223165
66 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool