Recoding Error-Correcting Output Codes

Abstract. One of the most widely applied techniques to deal with multiclass 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...

• Type: Conference
• Year: 2009
• Where: MCS
• Authors: Sergio Escalera, Oriol Pujol, Petia Radeva
• Keywords: MCS 2009, Multiclass Categorization Problems, One-versus-one Coding Matrix, Pairwise Voting Procedure, Pattern Recognition