Air-Writing Character Recognition with Ultrasonic Transceivers

Dual-Backplate CMUTs With Wide Bandwidth and Low Driving Voltage for Airborne Applications

In this work, novel airborne capacitive micromachined ultrasonic transducers (CMUTs) based on a dual-backplate (DBP) technology are presented. In contrast to conventional CMUTs, these transducers use a three-electrode-based capacitive system, where the membrane is placed between two highly-perforated counter electrodes, enabling enlarged displacement amplitudes in electrostatic actuation and wide and tunable bandwidth (BW) due to a ventilated air cavity. Fabricated DBP-CMUT prototypes therefore show exceptionally high receive and transmit sensitivities of -34.5 dB(V/Pa) and 259 nm/V, respectively, in their 84-kHz resonance. The viscous dissipation introduced by ventilating the cavity results in a wide factional BW (FBW) of 29%. Applicability of the developed CMUT for airborne ranging is demonstrated in pulse-echo-based ranging measurements, where the distance of a sound-reflecting metal plate can be clearly detected by a single CMUT operated in a transceiver mode.

Recognition of Uni-Stroke Characters with Hand Movements in 3D Space Using Convolutional Neural Networks

Hand gestures are a common means of communication in daily life, and many attempts have been made to recognize them automatically. Developing systems and algorithms to recognize hand gestures is expected to enhance the experience of human-computer interfaces, especially when there are difficulties in communicating vocally. A popular system for recognizing hand gestures is the air-writing method, where people write letters in the air by hand. The arm movements are tracked with a smartwatch/band with embedded acceleration and gyro sensors; a computer system then recognizes the written letters. One of the greatest difficulties in developing algorithms for air writing is the diversity of human hand/arm movements, which makes it difficult to build signal templates for air-written characters or network models. This paper proposes a method for recognizing air-written characters using an artificial neural network. We utilized uni-stroke-designed characters and presented a network model with inception modules and an ensemble structure. The proposed method was successfully evaluated using the data of air-written characters (Arabic numbers and English alphabets) from 18 people with 91.06% accuracy, which reduced the error rate of recent studies by approximately half.