ASL Classification - Real-time American Sign Language Recognition

This project aims to develop a computer vision program for recognizing American Sign Language (ASL) hand gestures in real time. Using a machine learning model trained on an MNIST-style dataset with ASL data, the program interprets hand signs and classifies them into corresponding ASL letters or words.

Features

• Image Preprocessing: Efficient image preprocessing pipeline to normalize and prepare gesture images.
• Model Architecture: Leverages Convolutional Neural Networks (CNNs) to capture spatial features unique to each hand gesture.
• Real-time Recognition: Processes live video feed for real-time ASL recognition.
• User Interface: Interactive interface to display recognized ASL letters in real-time.

Tech Stack

• Python, OpenCV, TensorFlow, and Keras

Usage

Clone the repository, install dependencies, and run the script to start the ASL recognition program on your local machine.