HCI & Gesture / Signal InterfacesComputer Vision & Perception

Vision-based Hand Gesture Virtual Keyboard-Mouse

Completed

Vision-based hand-gesture virtual keyboard-mouse with bilingual (English/Bangla) LSTM next-word prediction — a low-latency touchless text-entry system (IEEE, JCSSE 2026).

Source code Paper

Vision-based hand gesture virtual keyboard and mouse interface in use

Overview

Developed a modular real-time pipeline integrating MediaPipe hand-landmark gesture recognition with bilingual LSTM next-word prediction in English and Bangla within a unified keyboard-mouse interface featuring performance monitoring, delivering a low-latency, resource-efficient touchless text entry solution for desktop and wearable devices.

Highlights

Hand Gesture Recognition
Bilingual Prediction
Touchless Interface

Tech stack & key skills

Core tools, methods and skills demonstrated in this project:

PythonMediaPipe (hand landmarks)LSTMBilingual next-word predictionReal-time gesture recognitionHuman-computer interaction