This paper concerns the continuity of vision based robot control law. Recently, we have proposed a way of allowing the temporary disappearance of image features during the control task based on weighted features. Futher more, we have redefined the camera invariant visual servoing approach in order to take into account the change of image features when zooming in or out during a positioning task. In this paper, we study ho to select some parameters of the weight function and we propose a local stability analysis of the invariant visual servoing approach with weighted features. Finally, experimental results demonstrate the improvements that can be achieved in the performance of vision-based control task.