본문 바로가기
  • Home

Performance Improvement of Facial Gesture-based User Interface Using MediaPipe Face Mesh

  • Journal of Internet of Things and Convergence
  • Abbr : JKIOTS
  • 2023, 9(6), pp.125-134
  • DOI : 10.20465/KIOTS.2023.9.6.125
  • Publisher : The Korea Internet of Things Society
  • Research Area : Engineering > Computer Science > Internet Information Processing
  • Received : September 29, 2023
  • Accepted : November 23, 2023
  • Published : December 29, 2023

JinWang Mok 1 Noyoon Kwak 2

1광주과학기술원
2백석대학교

Accredited

ABSTRACT

The purpose of this paper is to propose a method to improve the performance of the previous research is characterized by recognizing facial gestures from the 3D coordinates of seven landmarks selected from the MediaPipe Face Mesh model, generating corresponding user events, and executing corresponding commands. The proposed method applied adaptive moving average processing to the cursor positions in the process to stabilize the cursor by alleviating microtremor, and improved performance by blocking temporary opening/closing discrepancies between both eyes when opening and closing both eyes simultaneously. As a result of the usability evaluation of the proposed facial gesture interface, it was confirmed that the average recognition rate of facial gestures was increased to 98.7% compared to 95.8% in the previous research.

Citation status

* References for papers published after 2023 are currently being built.

This paper was written with support from the National Research Foundation of Korea.