A Probabilistic Modeling Approach to One-Shot Gesture Recognition

TL;DR

This paper introduces a hierarchical probabilistic model for one-shot gesture recognition, enabling user-defined gestures with minimal training data, demonstrated on a Myo sensor bracelet with promising results.

Contribution

It presents a novel probabilistic framework that leverages shared features to reduce training data needed for new gestures, enhancing customization in gesture recognition systems.

Findings

Favorable recognition results on 17 gesture types

Effective incorporation into real-time systems

Reduced training examples for new gestures

Abstract

Gesture recognition enables a natural extension of the way we currently interact with devices. Commercially available gesture recognition systems are usually pre-trained and offer no option for customization by the user. In order to improve the user experience, it is desirable to allow end users to define their own gestures. This scenario requires learning from just a few training examples if we want to impose only a light training load on the user. To this end, we propose a gesture classifier based on a hierarchical probabilistic modeling approach. In this framework, high-level features that are shared among different gestures can be extracted from a large labeled data set, yielding a prior distribution for gestures. When learning new types of gestures, the learned shared prior reduces the number of required training examples for individual gestures. We implemented the proposed gesture classifier for a Myo sensor bracelet and show favorable results for the tested system on a database of 17 different gesture types. Furthermore, we propose and implement two methods to incorporate the gesture classifier in a real-time gesture recognition system.