AirPen: A Touchless Fingertip Based Gestural Interface for Smartphones and Head-Mounted Devices

TL;DR

AirPen is a real-time, touchless gestural interface for smartphones and head-mounted devices that uses lightweight deep learning models to recognize in-air hand gestures and writing with high accuracy and low latency.

Contribution

This work introduces AirPen, a novel lightweight deep learning framework enabling real-time in-air gesture recognition on mobile devices without additional hardware.

Findings

Achieves 80% gesture classification accuracy

Operates with an average latency of 0.12 seconds

Runs seamlessly on standard Android smartphones

Abstract

Hand gestures are an intuitive, socially acceptable, and a non-intrusive interaction modality in Mixed Reality (MR) and smartphone based applications. Unlike speech interfaces, they tend to perform well even in shared and public spaces. Hand gestures can also be used to interact with smartphones in situations where the user's ability to physically touch the device is impaired. However, accurate gesture recognition can be achieved through state-of-the-art deep learning models or with the use of expensive sensors. Despite the robustness of these deep learning models, they are computationally heavy and memory hungry, and obtaining real-time performance on-device without additional hardware is still a challenge. To address this, we propose AirPen: an analogue to pen on paper, but in air, for in-air writing and gestural commands that works seamlessly in First and Second Person View. The models are trained on a GPU machine and ported on an Android smartphone. AirPen comprises of three deep learning models that work in tandem: MobileNetV2 for hand localisation, our custom fingertip regression architecture followed by a Bi-LSTM model for gesture classification. The overall framework works in real-time on mobile devices and achieves a classification accuracy of 80% with an average latency of only 0.12 s.