Hardware Features: A glove fitted with 5 flex sensors (one per finger) An MPU6050 accelerometer/gyroscope module for motion detection An ESP32 microcontroller for data collection and wireless communication 3D-printed mounts for sensor precision Real-time Wi-Fi/Bluetooth data transmission Software Pipeline: Arduino IDE: Programming ESP32 and managing sensor input Python (VS Code): Gesture classification using Scikit-learn, TensorFlow, and Keras Flask Web App: Displays translations in real time SQLite/MySQL Database: Stores gesture sets, models, and user data 🔁 The system is scalable and currently supports predefined signs, with potential to grow into full sign language dictionaries. It aims to be affordable, intuitive, and empowering—truly giving voice to the unspoken.  

Idea: Un-Mute is a wearable glove-based system that captures hand and finger movements used in sign language and translates them in real time into spoken or written text using a mobile/web app. It leverages: Flex sensors MPU6050 motion tracking Machine learning models This allows for accurate recognition and classification of sign gestures, promoting seamless communication between signers and non-signers. Objectives: 🧤 Develop a low-cost wearable device to accurately interpret sign gestures 🎯 Use flex sensors and motion tracking to capture finger and hand movements 🧠 Design a machine learning pipeline to classify signs into alphabets, words, or sentences 📲 Build a user-friendly app interface that displays translated output as text or speech 🌐 Promote inclusivity between Deaf and hearing communities 🔓 Ensure the system is open-source and customizable for broader impact and innovation