[Company Logo Image]  (*)

Home Up Feedback Contents Search


HeadWheelchair ClipOn EMG SmartSpeakingKeyboard Virtual Multi Stereopsis Plant Phenotype 3D using Octree Limb-Volume measurement using Infrared Depth Sensor Object_Recognition Scene Understanding Field Phenotyping Background Subtraction Human Motion Calibration of VSNs Image-Based Servoing Robot Navigation Path Planning Inverse Kinematics Target Tracking Target Geolocation ODI Virtual Dermatologist CNN Virtual Machines for Image Processing New Models for Parallel Soft Computing



Smart Speaking Keyboard

                                                                             by Isma Hadji


   People with severe disabilities struggle to do plenty of daily life tasks one of which is speaking and therefore communicating with people. In fact, loosing such ability is very frustrating and debilitating. For this reason, in this project we propose an implementation of a “smart” speaking keyboard that can be controlled through and EMG signal to suit the needs of severely disabled people whose only way of communication is the EMG signals that they can generate.

System description

   This project proposes a communication solution for severely disabled people. In its very basic form, the proposed tool will be able to continuously display and read letters of the alphabet to the user on a small size screen connected to a raspberry Pi which will act as the brain of the system. Whenever the user expresses the need to write or say something he can interact with the system through EMG signals that can be generated by any movement that the user can achieve. As soon as the user triggers an EMG signal the program responds accordingly. Once a sentence is formed the program will read the sentence for the user if he expresses the need to through another EMG signal as well. To be able to talk to people when they are not close to the user, the proposed tool will be able to communicate with another raspberry Pi equipped with speakers provided that the two devices have a mean of network communication for that matter. The type of EMG signals are read and decoded by another external device that sends information about the signal through WIFI to the main Pi. The overall system is described in figure 1. The software part is built around 2 main threads and 2 sockets as depicted in figure 2.

Demo Video











Home ] Up ]

Send mail to webmaster@ee.missouri.edu with questions or comments about this web site.
Last modified: 06/26/16
(*) Logo created by James Wong