Vision-based Hand Gesture Virtual Keyboard-Mouse Framework with Bilingual Next-word Prediction
JCSSE 2026 — 23rd Int'l Joint Conf. on Computer Science & Software Engineering · To be presented · June 24–27, 2026
JCSSE 2026 conference paper: a real-time touchless keyboard-mouse pairing MediaPipe hand-landmark gestures with bilingual (English/Bangla) LSTM next-word prediction.
Authors
Mahdi, S., Karim, R. U., Sujat, T., Tabassum, S. M., Samin, A., Zereen, A. N. — Co-author
Contribution
A modular, real-time touchless keyboard-mouse that pairs geometric encoding of MediaPipe hand landmarks with two-layer LSTM bilingual (English/Bangla) next-word prediction — 9 static gestures at 97.4%+ accuracy and up to 37.7 FPS, with character error rates of 3.43% (English) and 8.34% (Bangla).
Topics
Cite
Mahdi, S., Karim, R. U., Sujat, T., Tabassum, S. M., Samin, A., & Zereen, A. N. (2026). Vision-based Hand Gesture Virtual Keyboard-Mouse Framework with Bilingual Next-word Prediction. JCSSE 2026.