As part of our work on hand gesture inter pretation, we present our results on hand shape rec ognition. Our method is based on attribute extraction and multipl e binary SVM classification. The novelty lies in th e fashion the fusion of all the partial classificatio n results are performed. This fusion is (1) more ef ficient in terms of information theory and leads to more accur ate result, (2) general enough to allow other sourc e of information to be taken into account: Each SVM output is transformed to a belief function, and all the corresponding functions are fused together with some other external evidential sources of information.