PRTools Contents

PRTools User Guide



Compute the error-reject trade-off curve

    E = REJECT(D);
    E = REJECT(A,W);

 D Classification result, D = A*W
 A Dataset
 W Cell array of trained classifiers

 E Structure storing the error curve and information needed for plotting


E = REJECT(D) computes the error-reject curve of the classification  result D = A*W, in which A is a dataset and W is a classifier. E is  a structure storing the error curve in E.ERROR. Use PLOTE(E) for  plotting the result.

    E = REJECT(A,W) computes a set of error-reject curves for all trained 
classifiers stored in the cell array W.


 A - training set, B - test set:
 D = B*NMC(A); E = REJECT(D); PLOTE(E);   % Plots a single curve
 E = REJECT(B,A*{NMC,UDC,QDC}); PLOTE(E); % Plots 3 curves


1. R.O. Duda, P.E. Hart, and D.G. Stork, Pattern classification, 2nd edition, John Wiley and Sons, New York, 2001.
2. A. Webb, Statistical Pattern Recognition, John Wiley && Sons, New York, 2002.

See also

datasets, mappings, plote, prroc, testc,

PRTools Contents

PRTools User Guide

This file has been automatically generated. If badly readable, use the help-command in Matlab.