In this paper, the authors present a new classification method based on Support Vector Machine (SVM) to treat multi-class problems. In the context of multi-class problems, they have to separate large number of classes. SVM becomes an important machine learning tool to handle multi-class problems. Usually, SVM classifiers are implemented to deal with binary classification problems. In order to handle multiclass problems, they present a new method that builds dynamically a hierarchical structure from training data. Their multiclass method is based on three main concepts : hierarchical classification, fuzzy logic and SVM. They combine multiple binary SVMs to solve multi-class problems.