Elsevier

Pattern Recognition

Volume 31, Issue 10, October 1998, Pages 1579-1588
Pattern Recognition

CLASS-SELECTIVE REJECTION RULE TO MINIMIZE THE MAXIMUM DISTANCE BETWEEN SELECTED CLASSES

https://doi.org/10.1016/S0031-3203(97)00136-2Get rights and content

Abstract

Class-selective rejection scheme assigns to an input pattern a subset of classes that are most likely to identify the pattern, and not simply reject it. Conventional class-selective rejection rules can minimize the error rate for a given average number of classes. In this paper, an example of unnatural classification is shown by using conventional rules and a new optimum criterion for establishing a class-selective rejection rule is proposed. Its optimality and upper-bound of error rate are proven. Finally, two examples are provided to illustrate various aspects of this optimum decision rule.

References (0)

Cited by (18)

  • A family of measures for best top-n class-selective decision rules

    2012, Pattern Recognition
    Citation Excerpt :

    Ha extended it to inliers that can be associated with a subset of the known classes [5,6] leading to a class-selective rejection rule as opposed to Chow's rejection rule. In order to avoid unnatural decisions due to posterior probabilities normalization, Horiuchi proposed to test their differences [7] while Frélicot and Dubuisson had previously used their ratios [8]. This latter idea has been introduced again several times [9,10].

  • Set-valued Bayesian inference with probabilistic equivalence

    2012, Proceedings - International Conference on Pattern Recognition
  • Classification with reject options in a logical framework: A fuzzy residual implication approach

    2009, 2009 International Fuzzy Systems Association World Congress and 2009 European Society for Fuzzy Logic and Technology Conference, IFSA-EUSFLAT 2009 - Proceedings
View all citing articles on Scopus
View full text