It is well-known that mechanical sensors suffer failure in hostile environments. Therefore, in such applications, vision control is a suitable solution. In this paper, we propose a new approach for design and implementation of the control system for the speed of the coupler point in a four-bar linkage. To measure the coupler point position a computational vision system is implemented; the vision system sends the controller the precise position of the desired point for a wide range of crank rotational speeds. A proportional integral derivative control system is designed and implemented in a microprocessor. Stability analysis for the controlled system is performed via the Lyapunov stability theory. Performance of the system is validated experimentally in a prototype of a planar mechanism obtaining an average square error of measurement less than 0.03% and regulation of operating point less than 1% for different speed references.