An image assistive communication system with a real-time fuzzy-controlled image Morse code input (FCIMCI) function was developed to help severely disabled people, such as those with cerebral palsy (CP) or spinal cord injury (SCI), communicate with other people or machines by using lip shape image recognition without using any apparatus. The real-time FCIMCI system offers the functions of text input and mouse control, replacing the traditional keyboard and mouse. The self-developed image recognition techniques include skin color detection, face-shape confirmation, lip location, and opened/closed lip status identification for Morse code conversion. In this paper, we apply the adjustable fuzzy recognition algorithm to tune the threshold values automatically for identifying Morse code. The experimental results of real-time lip image recognition show an average accuracy rate higher than 94% under various environmental conditions. Meanwhile, the average accuracy rate of image Morse code recognition experiments is more than 93.85%. According to the experimental results and a case study of SCI, we demonstrate that the FCIMCI system has real-time performance and good recognition efficiency. It is a novel assistive communication system based on image Morse code techniques and has the practicality and feasibility to help severely disabled people communicate with others.
All Science Journal Classification (ASJC) codes