Significance Test for Feature Subset Selection on Image Recognition

  • Qianren Xu
  • M. Kamel
  • M. M. A. Salama
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3211)


This paper proposes a novel feature selection method based on significance test (ST). Statistical significant difference between (or among) classes, such as t statistic in Student test and F statistic in ANOVA, is utilized to measure pattern recognition ability of individual features. The feature significance level during a feature selecting procedure is used as feature selection criterion, which is determined by the product of the significant difference level and the independent coefficient of the candidate feature. An algorithm of maximum significant difference and independence (MSDI) and strategies of monotonically increasing curve (MIC) are proposed to sequentially rank the feature significance and determine the feature subset with minimum feature number and maximum recognition rate. Very good performances have been obtained when applying this method on handwritten digital recognition data.


Feature selection maximum significant difference and independence (MSDI) significance test t-test ANOVA correlation 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Battiti, R.: Using mutual information for selecting features in supervised neural net learning. IEEE Trans. Neural Network 5, 537–550 (1994)CrossRefGoogle Scholar
  2. 2.
    Thawonmas, R., Abe, S.: A novel approach to feature selection based on analysis of fuzzy regions. IEEE Trans. Systems, Man, and Cybernetics Part B 27, 196–207 (1997)CrossRefGoogle Scholar
  3. 3.
    Cover, T.M., Van Campenhout, J.M.: On the Possible Orderings in the Measurement Selection Problem. IEEE Trans. Systems, Man, and Cybernetics 7, 657–661 (1977)zbMATHCrossRefMathSciNetGoogle Scholar
  4. 4.
    Wonnacott, R.J., Wonnacott, T.H.: Introductory Statistics, 4th edn. John Wiley & Sons, Chichester (1996)Google Scholar
  5. 5.
    Wasserman, P.D.: Advanced Methods in Neural Computing, pp. 35–55. Van Nostrand Reinhold, New York (1993)zbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Qianren Xu
    • 1
  • M. Kamel
    • 1
  • M. M. A. Salama
    • 2
  1. 1.Dept. of System Design EngineeringUniversity of WaterlooWaterlooCanada
  2. 2.Dept. of Electrical and Computer EngineeringUniversity of WaterlooWaterlooCanada

Personalised recommendations