Deeplens Asl

Abstract

1. Introduction

The future is not in keyboards and mice. Everyone agrees on the fact that interaction with computers will mainly use voice in the coming years. Siri, Cortana, Google Home, and, of course, Alexa (and Alexa for Business) are all examples of what the future may be. Even Werner Vogels thinks voice interaction will be the new traditional interaction (Nov’ 2017).

However, if nearly everybody can speak to a computer, removing the need for literacy (mandatory with a keyboard), some people in the society are still put apart: those who can’t speak. Whether they are deaf-and-dumb, or they don’t know the right languages (e.g. Foreigners or immigrates), they cannot interact with conversational agents.

The Deeplens may help them understand those who can’t speak, thanks to the American Sign Language (or some variants). The processing of video flow and a deep learning model can leverage the Deeplens as a new interface for them, translating ASL to written / spoken English in real time, so as to interact with computers.

2. Objective

American Sign Language detection with AWS DeepLens

This project demonstrates how Python can be applied to a real-world AI & Machine Learning problem.

4. Technology Stack

5. System Requirements

General requirements for this technology stack — check the README for exact versions.

• Python 3.8 or later
• pip / virtualenv for dependencies
• VS Code, PyCharm or Jupyter Notebook
• Git (to clone the repository)

6. Installation & Setup

git clone https://github.com/bmeudre/deeplens-asl.git
cd deeplens-asl

Full setup instructions are in the project README.

7. Future Enhancements

Suggested extensions you can add to make this your own project.

• Deploy the model as a web app with Streamlit, Flask or FastAPI
• Compare against an additional model and report the metric difference
• Add explainability (SHAP / Grad-CAM)

8. Viva / Review Questions

Common questions examiners ask for projects in this domain.

1. What dataset does the project use and how was it pre-processed?
2. Which algorithm / model architecture is used and why was it chosen over alternatives?
3. How are training and testing data split, and how is overfitting avoided?
4. Which evaluation metrics (accuracy, precision, recall, F1) are reported and what do they mean here?
5. How would you deploy this model for real users?

9. Source Code & License

This project is developed by bmeudre and published on GitHub under the MIT License. Please follow the license terms and credit the original author when you use or modify this code.