Eigengestures for natural human computer interface

TL;DR

This paper explores the use of Principal Component Analysis to develop eigengestures for natural human-computer interaction, demonstrating how dimensionality reduction affects gesture data quality.

Contribution

It introduces the concept of eigengestures for motion capture data and visualizes principal components for natural gesture interface design.

Findings

Principal components effectively represent gesture data

Dimensionality reduction impacts gesture reconstruction quality

Visualizations aid in understanding gesture variations

Abstract

We present the application of Principal Component Analysis for data acquired during the design of a natural gesture interface. We investigate the concept of an eigengesture for motion capture hand gesture data and present the visualisation of principal components obtained in the course of conducted experiments. We also show the influence of dimensionality reduction on reconstructed gesture data quality.