We present in this paper a new palmprint recognition system based on the principal lines of the palm. An original algorithm is proposed in order to detect automatically principal lines and extract their corre-spondent geometrical features. Given the complexity of the palmprint recognition and in order to ameliorate performances, we propose a hybrid approach based on both geometrical and gabor features. A comparative study between the three feature vectors obtained from the geometrical approach, global approach and combination of both has proved that the geometrical features are the most relevant since they can give the best compromise recognition Rate/Time. Moreover, a combination of geometrical features with global features can improve recognition rate while keeping the same recognition and learning times. Obtained results also show that the hybrid approach performances are very satisfactory and even surpass the very popular ones.
展开▼