Outliers in statistical pattern recognition and an application to automatic chromosome classification

Abstract

We propose a heuristic method of parameter estimation in mixture models for data with outliers and design a Bayesian classifier for assignment of m objects to n ⩾ m classes under constraints. This method of outlier handling combined with the classifier is applied to the well-known problem of automatic, constrained classification of chromosomes into their biological classes. We show that it decreases the error rate relative to the classical, normal, model by more than 50%. When applied to the Edinburgh feature data of the large Copenhagen image data set Cpr our best classifier yields an error rate close to 1.3% relative to chromosomes; 4 out of 5 cells are correctly classified.