Development of a Compact System to Recognize 26 Letters in American Sign Language Alphabet Based on Flexible Ionic Liquid Strain Sensors
Chi Tran Nhu, Tiep Dang Dinh, Phu Nguyen Dang, Van Nguyen Thi Thanh, Cuong Vu Manh, Tung Thanh Bui · 2023
In this paper, a sign language recognition system is presented and successfully implemented using self-developed strain sensors based on ionic liquid and uses five strain sensors attached to the fingers via a glove for detecting the relative positions of the fingers. The signals from the sensors are transmitted to a data acquisition and processing circuit system, where an algorithm decodes the data into alphabet letters. The sensitivity of the flexible ionic sensors and the functioning circuit of the system were evaluated before being integrated into the system. The experimental results showed that the ionic sensors are suitable for this application and the proposed system can recognize 26 letters in the American Sign Language alphabet (ASL) with high accuracy, up to 98.27%. A graphical user interface on a PC was also developed to convey information in the form of text and speech, enabling communication with deaf people without the need for learning sign language. This low-cost sign language recognition system has the potential to improve communication between deaf.