Bayes Error Estimation Using Parzen and k-NN Procedures

DOI10.1109/TPAMI.1987.4767958zbMath0628.62031OpenAlexW1983963519WikidataQ84833240 ScholiaQ84833240MaRDI QIDQ3765035

Donald M. Hummels, Keinosuke Fukunaga

Publication date: 1987

Published in: IEEE Transactions on Pattern Analysis and Machine Intelligence (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1109/tpami.1987.4767958

zbMATH Keywords

nearest neighborbiasesfinite samplenumber of samplesk-NNeffect of kernel size and shapeestimates of the Bayes errorlimited design set conditionsParzen density estimates

Mathematics Subject Classification ID

Nonparametric estimation (62G05)

Related Items (9)

Statistical decisions under nonparametric a priori information ⋮ A discriminant analysis using composite features for classification problems ⋮ A vision-based method for weeds identification through the Bayesian decision theory ⋮ Mahalanobis distance-based two new feature evaluation criteria ⋮ On evaluating a class of frame-based nonstationary pattern recognition methods using Bhattacharyya distance ⋮ Overlap pattern synthesis with an efficient nearest neighbor classifier ⋮ Optimal selection of reference set for the nearest neighbor classification by tabu search ⋮ Cluster analysis by adaptive rank-order filters ⋮ Optimal reference subset selection for nearest neighbor classification by tabu search

This page was built for publication: Bayes Error Estimation Using Parzen and k-NN Procedures