Gaze estimation algorithms in C++ using laptop's camera as input and machine learning algorithms for the prediction of gaze's direction.

Minimalist (Spotify) music player built around open hardware design intended to enable people with cognitive or physical disabilities to enjoy music on their own.

🎙️ Welcome to the Speech to Text Application! 📝 This tool converts your spoken words into text in real time. With a sleek, modern interface powered by `customtkinter`, you can easily integrate this solution into your streaming setup or any project that needs speech-to-text capabilities. 🌟

Navigation Assistant For Visually Restricted And Aided Humans (N.A.V.R.A.A.H.): An intelligent assistive framework integrating Raspberry Pi and Arduino to enable real-time object detection via TensorFlow and haptic-audio feedback for safer, independent navigation.

The backend for the BlueScript app, open source program for aiding dyslexia.

A smart glasses project that runs on YOLOv8's object detection network

Integrate you terminal with AI capabilities

Blink to Survive - is a hands-free accessibility tool that lets you play the famous **Chrome Dino Game** using just your eyes! With a simple blink, your dinosaur will jump over obstacles — no keyboard or mouse needed.

SWheels - Smart Autonomous Voice-Controlled Wheelchair

Math Typing Application for those with Learning Disabilities

Blink Music Controller is a Python tool that allows users to control their media playback using only their eye blinks. it simulates keyboard shortcuts such as play/pause, next/previous track, and seek actions, based on blink gesture so no hands required.

Allowing visually impaired users to hear images live as they are recorded by transforming greyscale image data into sounds by mapping brightness → amplitude, pixels(x, y) → frequency (using pseudo-Hilbert-curves and Fourier transformations for 2D → 1D mapping)

🤗 LeRobot: Feeder and Voice AI Assistant for the Mobility Divergent

Minimal Bookkeeping for peope with need for simplicity

This project focuses on translating sign language gestures into text using deep learning and computer vision.