mlh-fellowship/teamkerberos_pod1.0.2

A way to connect everyone in this virtual world. An application for hearing/speech impaired people to make it easy for them to communicate in this pandemic.

ASL Translator

This project is a sign language alphabet recognizer using Python, openCV and tensorflow for training InceptionV3 model, a convolutional neural network model for classification.

The framework used for the CNN implementation can be found here:

Simple transfer learning with an Inception V3 architecture model by xuetsing

This is the demo repository of our first hackathon at MLH-Fellowship Fall'2020.

Installation and Setup

Setup and running of project (Backend)

• Fork the repo and clone it.
• The project now uses pipenv to manage dependencies.
• Install Pipenv using the following command:

pip install pipenv

• Navigate to the project directory and initialize the environment using the following command -

pipenv shell --python 3.5

• The above step also activates the environment, for activating the environment in subsequent sessions type the following command:

pipenv shell

• At the root of your project directory
  

pipenv install
pre-commit install

• This will setup the project requirements and pre-commit test hooks!

• Then run the following command to run the backend service -

python server/app.py

• This will run the project at localhost:5001

Contribution to the project

We follow a systematic Git Workflow -

• Create a fork of this repo.
• Clone your fork of your repo on your pc.
• Add Upstream to your clone
• Every change that you do, it has to be on a branch. Commits on master would directly be closed.
• Make sure that before you create a new branch for new changes,syncing with upstream is neccesary.

Commits

• Write clear meaningful git commit messages (Do read this).
• Make sure your PR's description contains GitHub's special keyword references that automatically close the related issue when the PR is merged. (Check this for more info)
• If you're making very, very small changes to your PR (such as fixing a failed Travis build, or making some minor style corrections or minor changes requested by reviewers), make sure you squeeze your commits afterwards, so you don't have an absurd number of commits for a very small fix. (Learn how to squash at here)
• If you are submitting a PR for a UI-related topic, it would be really awesome if you could add a screenshot of your change or a link to a deployment where it can be tested along with your PR. This makes it very easy for reviewers and you will also get reviews faster.

Contributors

Maintainers of the project

Amazing members of Team Kerberos!

Shubhank Saxena 💻 🎨 🚧

Abhishek Chaurasia 💻 🎨 🚧

Shreya Gupta 💻 🎨 🚧

teamkerberos_pod1.0.2's Issues

Improve Readme

The readme file should have the following steps -

• Contribution method
• Setup steps
• Contributors list (improved)
• Future enhacnements

Issue raising template needs to be added

So that the new issues are following some pre-required steps and checks!

Modularity of UI

Need to enhance the UI to fit our needs of the project.

• Work on pane distribution
• Need to work on user management

Text Append issue

Currently, all the translated text is being presented by one character only. Need to fix that and make sure that all of the presented characters are appended one after other to form a proper word.

Client side rendering

Need to program the client side rendering of the endpoint to access browser device API so that we can use the client camera