%0 Conference Proceedings
%T Recoding Error-Correcting Output Codes
%A Sergio Escalera
%A Oriol Pujol
%A Petia Radeva
%B 8th International Workshop of Multiple Classifier Systems
%D 2009
%V 5519
%I Springer Berlin Heidelberg
%@ 0302-9743
%@ 978-3-642-02325-5
%F Sergio Escalera2009
%O MILAB;HuPBA
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=1190), last updated on Tue, 17 Dec 2013 16:34:19 +0100
%X One of the most widely applied techniques to deal with multi- class categorization problems is the pairwise voting procedure. Recently, this classical approach has been embedded in the Error-Correcting Output Codes framework (ECOC). This framework is based on a coding step, where a set of binary problems are learnt and coded in a matrix, and a decoding step, where a new sample is tested and classified according to a comparison with the positions of the coded matrix. In this paper, we present a novel approach to redefine without retraining, in a problem-dependent way, the one-versus-one coding matrix so that the new coded information increases the generalization capability of the system. Moreover, the final classification can be tuned with the inclusion of a weighting matrix in the decoding step. The approach has been validated over several UCI Machine Learning repository data sets and two real multi-class problems: traffic sign and face categorization. The results show that performance improvements are obtained when comparing the new approach to one of the best ECOC designs (one-versus-one). Furthermore, the novel methodology obtains at least the same performance than the one-versus-one ECOC design.
%U http://dx.doi.org/10.1007/978-3-642-02326-2_2
%P 11–21