Gesture Based Media Controller
A Python-based application that allows users to control media player functions (Play, Pause, Volume Up, Volume Down, etc.) using hand gestures detected through the webcam. This project uses MediaPipe and OpenCV for real-time hand tracking and gesture recognition, providing a hands-free, interactive experience for media control.
— view project
AI-Agent
AI-Agent is a FastAPI application that allows you to upload PDFs, extract their text, and query the content using a local AI model (Orca Mini 3B). The app runs entirely offline, ensuring that no data leaves your device.
— view project
FaceViT
Facial Emotion Extraction using Vision Transformers
A real-time facial expression analysis system that tracks a user’s emotions while they watch a video. The admin uploads a video, and the system uses a Vision Transformer–based model to detect expressions via webcam and generate a text summary of emotional responses for documentation.