Automatical Definition of Measures from the Combination of Shape Descriptors
Résumé
This paper presents a novel approach to combine shape descriptors. Each approach is applied on several clusters of objects. For each cluster and for any descriptor a map is as-sociated directly from the confusion matrix. Such a method allows to determine automatically the better weight asso-ciated to the descriptor for the object under consideration. At last, we show that the additive combination of such mea-sures allows to improve the classification.