A Helping Hand: Gestures Recognition using Android Mediapipe
MATRIX Academic International Online Journal Of Engineering And Technology · 2025
DOI: 10.21276/matrix.2025.8.1.1 ↗Kurz gefasst
Fachartikel in der Zeitschrift MATRIX Academic International Online Journal Of Engineering And Technology, 2025. Verfasst von Shivam Roy und 1 weiteren Autor:innen.
Abstract (Originalsprache)
This paper presents a work related to multimodal automatic gesturesrecognition during human interaction. There was a dedicated database prepared;participants completed tasks based on a command-based structure to realize eightdifferent emotional states. There were three primary feature extraction methodsadopted in the system: facial expression recognition, gesture analysis throughMediaPipe, and acoustic analysis. MediaPipe, which runs on machine learningfor gesture tracking and detection, was crucial for hand movement analysis. Itused algorithms like CNNs for key hand landmarks’ detection in making thegesture recognition process more accurate. Then, it applied a Bayesian classifierfor automatically classifying the emotions based on data. Three types of datawere tested: unimodal (single input), bimodal (two inputs), and multimodal (allthree inputs together). This was either pre or post-classification. The outcomeof these experiments was that multimodal fusion improved recognition rates bymore than 10% compared to the best unimodal system. Of these combinations,‘gesture-acoustic’ proved most effective. The use of all three types of dataresulted in further improvements above the best bimodal combination.
Zitieren
APA
Roy, S., & Singh, A. (2025). A Helping Hand: Gestures Recognition using Android Mediapipe. MATRIX Academic International Online Journal Of Engineering And Technology. https://doi.org/10.21276/matrix.2025.8.1.1
Vancouver
Roy S, Singh A. A Helping Hand: Gestures Recognition using Android Mediapipe. MATRIX Academic International Online Journal Of Engineering And Technology. 2025. doi:10.21276/matrix.2025.8.1.1
BibTeX
@article{Roy2025,
author = {Roy, Shivam and Singh, Anuj},
title = {A Helping Hand: Gestures Recognition using Android Mediapipe},
journal = {MATRIX Academic International Online Journal Of Engineering And Technology},
year = {2025},
doi = {10.21276/matrix.2025.8.1.1}
}
EUVIMED