Deep ANN-based Touch-less 3D Pad for Digit Recognition

TL;DR

This paper introduces a touch-less 3D digit recognition system using a capacitance sensor and neural networks, providing a privacy-preserving, low-computation alternative to camera-based methods for public use.

Contribution

It presents a novel touch-less digit recognition approach using capacitance sensing and neural networks, avoiding image processing for privacy and efficiency.

Findings

High accuracy in recognizing handwritten digits in air

Low computational requirements due to non-image-based sensing

Suitable for implementation in public environments

Abstract

The Covid-19 pandemic has changed the way humans interact with their environment. Common touch surfaces such as elevator switches and ATM switches are hazardous to touch as they are used by countless people every day, increasing the chance of getting infected. So, a need for touch-less interaction with machines arises. In this paper, we propose a method of recognizing the ten decimal digits (0-9) by writing the digits in the air near a sensing printed circuit board using a human hand. We captured the movement of the hand by a sensor based on projective capacitance and classified it into digits using an Artificial Neural Network. Our method does not use pictures, which significantly reduces the computational requirements and preserves users' privacy. Thus, the proposed method can be easily implemented in public places.