Preprint

Electromyography-Based Sign Language Recognition: A Low-Channel Approach for Classifying Fruit Name Gestures

Kudratjon ZohirovSoftware and Hardware Support of Computer Systems , Karshi State Technical University , Karshi , UzbekistanMirjakhon TemirovConvergence of Digital Technologies , Tashkent University of Information Technologies , Tashkent , UzbekistanSardor BoykobilovSoftware and Hardware Support of Computer Systems , Karshi State Technical University , Karshi , UzbekistanGolib BerdievSoftware and Hardware Support of Computer Systems , Karshi State Technical University , Karshi , UzbekistanFeruz RuziboevConvergence of Digital Technologies , Tashkent University of Information Technologies , Tashkent , UzbekistanKhojiakbar EgamberdievComputer Systems , University of Economics and Pedagogy , Karshi , UzbekistanMamadiyor SattorovSoftware and Hardware Support of Computer Systems , Karshi State Technical University , Karshi , UzbekistanGulmira PardayevaInformation Technology , University of Information Technology and Management , Karshi , UzbekistanKuvonch MadatovComputer Systems , University of Economics and Pedagogy , Karshi , Uzbekistan

2025en

ABI

Annotatsiya

This paper presents a method for recognizing sign language gestures corresponding to fruit names using electromyography (EMG) signals. The proposed system focuses on classification using a limited number of EMG channels, aiming to reduce classification process complexity while maintaining high recognition accuracy. The dataset (DS) contains EMG signal data of 46 hearing impaired people and descriptions of fruit names, including apple, pear, apricot, nut, cherry, raspberry, in sign language (SL). Based on the presented DS, gesture movements were classified using 5 different classification algorithms - Random Forest, k-Nearest Neighbors, Logistic Regression, Support Vector Machine and Neural Networks, and it was analyzed which algorithm gives the best result for gesture movements. The best classification result was obtained during recognition of the word cherry based on the RF algorithm, and 97% accuracy was achieved.

Hali tarjima qilinmagan

Identifikatorlar

DOI: 10.20944/preprints202506.1537.v1

Iqtiboslar va manbalar

0 ta iqtibos0 ta foydalanilgan manba