On fusion schemes for multiclass object classification with reject in a given ensemble of sources

Abstract

Given ensemble of the different modality sources, we investigated two data fusion schemes for constructing metric-based multiclass classifiers with a reject option. The decisions made for the composite objects given by the collections of the source objects of the same class with one object per each source. The fusion schemes are based on using different compositions. The first scheme uses the composition of the decisions on the objects of the individual sources and this scheme is known as the fusion by the weighted majority vote or WMV scheme. The second scheme uses the composition in a form of the general dissimilarity measure between any pair of the composite objects. This scheme is original and it is called by GDM scheme. We constructed multiclass classifiers as the appropriate collections of NN or SVM elementary “class-vs-all” classifiers. We performed classification experiments in the ensemble of decorrelated components of face RGB images. We shown that GDM scheme gives fewer error rates with respect to WMV scheme.