2010 Volume 20 Pages 171-182
Finger Braille is one of the communication methods utilized by deafblind individuals. In one-handed Finger Braille, a sender dots the left part of the Braille code on the distal interphalangeal (DIP) joints of the index, middle and ring fingers of a receiver, and subsequently dots the right part of the Braille code on the proximal interphalangeal (PIP) joints of the same fingers. Since there is a limited number of non-disabled people who are skilled in Finger Braille, deafblind individuals communicate only through interpreters. To assist communication between deafblind individuals and non-disabled people, we have developed a Finger Braille recognition system. In the present study, we analyzed the shock accelerations from the dotting of one-handed Finger Braille. The receiver wore small piezoelectric accelerometers on the bases of the index, middle and ring fingers. Each accelerometer measured the acceleration attributed to the dotting of the sensor-mounted finger (self dotting) and the acceleration from the dotting of the other fingers (cross talk). We analyzed the shock accelerations from self dotting and cross talk and then derived an algorithm for the recognition of dotted fingers. The estimated recognition accuracy of dotted fingers was 92.9%, when the sender and the receiver sat side by side. We also derived an algorithm for the recognition of the dotted position (DIP and PIP joints). The estimated recognition accuracy for the dotted positions was 81.9% in the identical seating position.
