In the literature, the introduction of the reject option in multiple classifier systems has been analysed only from the experimental point of view. Following a first theoretical analysis provided by the authors, we analyse, within the framework of the minimum risk theory, the problem of finding the best error-reject trade-off achievable by a linear combination of a given set of trained classifiers. An algorithm for computing the parameters of the linear combination and of the reject rule is then proposed. Experimental results on two data sets of remote-sensing images are reported.
A method for error rejection in multiple classifier systems
2001-01-01
472658 byte
Conference paper
Electronic Resource
English
A Method for Error Rejection in Multiple Classifier Systems
British Library Conference Proceedings | 2001
|A Novel Support Vector Classifier with Better Rejection Performance
British Library Conference Proceedings | 2003
|Boosting with Multiple Classifier Families
British Library Conference Proceedings | 2007
|