• Matlab Pattern Recognition Toolbox for representation and generalization


  • More than 250 dedicated pattern recognition routines
  • About 400 support routines
  • representation, feature extraction and selection
  • pre-processing of raw data files included in the toolbox
  • integrated handling of data in files and data in RAM
  • linear and non-linear transformations
  • crisp, soft and target labels
  • multi-labeling system
  • more than 25 different classifiers
  • large set of combining classifiers
  • crossvalidation, learning curves, feature curves, EOC

Typical Usage

  • prototyping of recognition systems including preprocessing
  • the analysis of new data by standard tools
  • comparative studies for evaluating new, advanced tools.
  • student courses




  • The toolbox is used for the book. “Classification, parameter estimation and state estimation – an engineering approach using Matlab” (2004) by Ferdi van der Heijden, Robert P.W. Duin, Dick de Ridder and David M.J. Tax. More on the book