madhu-sv/asl-sign-language-recognition

Real-time ASL Sign Language Recognition using CNN

ASL Sign Language Recognition

This repository contains code for training and evaluating a Convolutional Neural Network (CNN) model to recognize American Sign Language (ASL) signs in real-time using a webcam.

Table of Contents

• Introduction
• Setup
  • Windows
  • macOS
  • Linux
• Training the Model
• Evaluating the Model
• Real-time Detection
• Google Colab Notebook

Introduction

This project uses a CNN to recognize ASL signs from images. The model is trained on a dataset of ASL images and can be used for real-time recognition through a webcam.

Setup

Prerequisites

• Python 3.x
• Virtual environment tool (optional but recommended)

Windows

1. Clone the Repository:

   git clone https://github.com/madhu-sv/asl-sign-language-recognition.git
   cd asl-sign-language-recognition```

2. Set Up a Virtual Environment:

   python -m venv venv
   venv\Scripts\activate

3. Install Dependencies:

   pip install -r requirements.txt

macOS

1. Clone the Repository:

   git clone https://github.com/madhu-sv/asl-sign-language-recognition.git
   cd asl-sign-language-recognition\

2. Set Up a Virtual Environment:

   python -m venv venv
   venv\Scripts\activate

3. Install Dependencies:

   pip install -r requirements.txt

Training the Model

1. Prepare the Dataset:

   • Download the ASL dataset and place it in the data directory.
   • Ensure the directory structure is as follows:

     data/
       ├── asl_alphabet_train/
       └── asl_alphabet_test/
     

2. Run the Training Script:

   python src/train.py

3. Output:

   • The trained model will be saved in the models directory as asl_model.h5.

Evaluating the Model

1. Run the Evaluation Script:

   python src/evaluate.py

2. Output:

   • The script will print the test accuracy of the model.

Real-time Detection

1. Run the Real-time Detection Script:

   python src/real_time_detection.py

2. Note:
   • This script uses OpenCV to access the webcam and perform real-time ASL recognition.
   • Ensure your webcam is connected and accessible.