Implementation of Eye-To-Text Morse Code Device to Help Speech Impairments People

This research aims to develop an Eye-to-Text Morse Code (ETT-MC) device as an assistive communication tool for individuals with speech disabilities, based on artificial intelligence image processing. The method used to detect speech codes is based on eye blink input, which is converted into Morse code and then translated into letters by utilizing a thresholding image processing technique that compares the pixel values when the eyes are open and closed. In Morse code, there are two main symbols combined to form a letter: the dash and the dot. The object of this research is the eye, where if the system detects the eye in an open state, it is converted into a dot code or value 1, while when the system detects the eye as closed, it is converted into a dash code or value 0. The results and hypotheses of this research show that the developed ETT-MC device can assist individuals with speech disabilities in communicating by utilizing eye blinks as an input medium to convey messages to others with an accuracy rate of up to 80%. This occurs because the accuracy of eye image detection processed by the system is significantly influenced by light intensity, the quality of the image detected by the camera, and the length of the translated text.