Domain Based LDA and QDA

We propose an alternative to probability density classifiers based on normal distributions LDA and QDA. Instead of estimating covariance matrices using the standard maximum likelihood estimator we estimate class domains by the minimum volume enclosing ellipsoid (-MVEE). The -MVEE is a robust statistic rejecting a specified fraction of the data. The performance of the domain and density approaches are compared in small sample size problems and in situations where sampling of a training and test sets is not i.i.d..

• Type: Conference
• Year: 2006
• Where: ICPR
• Authors: David M. J. Tax, Piotr Juszczak, Robert P. W. Duin, Serguei Verzakov
• Keywords: Computer Vision, ICPR 2006, Maximum Likelihood Estimator, Normal Distributions Lda, Probability Density Classifiers