Bayes Error Estimation Using Parzen and k-NN Procedures

DOI10.1109/TPAMI.1987.4767958MaRDI QIDQ3765035zbMATH OpenOpenAlexWikidataFDO

Authors Keinosuke Fukunaga, Donald M. Hummels

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

biaseseffect of kernel size and shapeestimates of the Bayes errorfinite samplek-NNlimited design set conditionsnearest neighbornumber of samplesParzen density estimates

Mathematics Subject Classification ID

Nonparametric estimation (62G05)

Recommendations

• A multiclass, k-NN approach to Bayes risk estimation
• The Nearest Neighbor and the Bayes Error Rates
• scientific article; zbMATH DE number 3962962
• Bias of Nearest Neighbor Error Estimates
• Validation of nearest neighbor classifiers

Cited in

(12)

• Mahalanobis distance-based two new feature evaluation criteria
• Statistical decisions under nonparametric a priori information
• Optimal reference subset selection for nearest neighbor classification by tabu search
• A vision-based method for weeds identification through the Bayesian decision theory
• Overlap pattern synthesis with an efficient nearest neighbor classifier
• A discriminant analysis using composite features for classification problems
• A multiclass, k-NN approach to Bayes risk estimation
• scientific article; zbMATH DE number 3962962 (Why is no real title available?)
• On evaluating a class of frame-based nonstationary pattern recognition methods using Bhattacharyya distance
• Optimal selection of reference set for the nearest neighbor classification by tabu search
• Cluster analysis by adaptive rank-order filters
• An arbitrarily tight lower bound for the Bhattacharyya upper bound on Bayes error

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

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3765035)