Performance Measurement of Gesture-Based Human-Machine Interfaces Within eXtended Reality Head-Mounted Displays

This paper proposes a method for measuring the performance of Human-Machine Interfaces based on hand-gesture recognition, implemented within eXtended Reality Head-Mounted Displays. The proposed method leverages a systematic approach, enabling performance measurement in compliance with the Guide to the Expression of Uncertainty in Measurement. As an initial step, a testbed is developed, comprising a series of icons accommodated within the field of view of the eXtended Reality Head-Mounted Display considered. Each icon must be selected through a cue-guided task using the hand gestures under evaluation. Multiple selection cycles involving different individuals are conducted to derive suitable performance metrics. These metrics are derived considering the specific parameters characterizing the hand gestures, as well as the uncertainty contributions arising from intra- and inter-individual variability in the measured quantity values. As a case study, the eXtended Reality Head-Mounted Display Microsoft HoloLens 2 and the finger-tapping gesture were investigated. Without compromising generality, the obtained results show that the proposed method can provide valuable insights into performance trends across individuals and gesture parameters. Moreover, the statistical analyses employed can determine whether increased individual familiarity with the Human-Machine Interface results in faster task completion without a corresponding decrease in accuracy. Overall, the proposed method provides a comprehensive framework for evaluating the compliance of hand-gesture-based Human-Machine Interfaces with target performance specifications related to specific application contexts.