Computer systems such as virtual environments and serious games are being used as a tool to enhance the process of user rehabilitation. These systems can help motivate and provide means to assess the user’s performance undertaking an exercise session. To do that, these systems incorporate motion tracking and gesture recognition devices, such as natural interaction devices like Kinect and Nintendo Wii. These devices, originally developed for the games market, allowed the development of low cost and minimally invasive rehabilitation systems, allowing the treatment to be taken to the patient’s residence. With the advent of natural interaction based on electromyography, devices that use electromyographic signals can also be used to construct these systems. The aim of this work is to show how electromyographic signals could be used as a tool to capture user gestures and incorporated into home-based rehabilitation systems by adopting a low-cost device to capture these gestures. The process of creation of a serious game to show some of these concepts is also present.