본문 바로가기
  • Home

IMU-Based Hand Gesture Recognition Using Prototypical Networks

  • Journal of Internet of Things and Convergence
  • Abbr : JKIOTS
  • 2025, 11(6), 22
  • Publisher : The Korea Internet of Things Society
  • Research Area : Engineering > Computer Science > Internet Information Processing
  • Received : November 11, 2025
  • Accepted : December 18, 2025
  • Published : December 31, 2025

Dong-Jin 1 Hyeong-Uk Park 2 Ji-Woong Choi 2 Won-Du Chang 2

1국립부경대학교 인공지능연구소
2국립부경대학교

Accredited

ABSTRACT

With the increasing importance of contactless interfaces in fields such as the metaverse, virtual reality (VR), and smart healthcare, hand gesture recognition technology has gained significant attention for enabling intuitive human-computer interaction. This study proposes a hand gesture recognition model based on Prototypical Networks that utilizes IMU sensor data collected from smartwatches. In experiments classifying ten types of numeric gestures collected from 15 subjects, the proposed model achieved an average accuracy of 86.20%. This study is expected to contribute to enhancing user convenience and system practicality in fields requiring contactless interfaces, such as smart healthcare and the metaverse, by enabling users to utilize personalized gestures without complex data collection processes.

Citation status

* References for papers published after 2024 are currently being built.