Controlling the upper limb prosthesis using muscular contractions requires the amputees intense and long period training, where frustration can lead to abandonment of the device. In this project we are proposing a Human Machine Interface (HMI) not only focused on muscular activity reading but in an innovative solution, based on computer vision. With a camera attached to the prosthesis, we desined a system that identifies objects, and suggests interactions based on the user's preferences.