Skip to content

This is a project that applies an ASL translation filter over a virtual camera which can then be used in teleconferences such as zoom, discord and skype.

Notifications You must be signed in to change notification settings

jerremyng/asl-filter

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

29 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

asl-filter

This is a data science project that applies an ASL translation filter over a virtual camera which can then be used in teleconferences such as zoom, discord and skype. It tracks landmarks on your body such as your face, hands and pose, feeding the data into a machine learning model to make a prediction on what word is being signed.

Built for iNTUition v8 hackathon https://devpost.com/software/unmuted

Quick start guide

Prerequisites

Download OBS Studio
Click "Start Virtual Camera" (bottom right), then "Stop Virtual Camera"
Close OBS

Usage

  1. Download repo
git clone https://github.com/jerremyng/asl-filter.git
  1. Install dependencies
pip install -r requirements.txt
  1. Run python script
python deploy_filter.py
  1. Then simply select the virtual camera from your video-calling app (zoom,skype,discord)

Signs available

The list of 6 words it can understand are found in the label_map.csv file ('afternoon', 'bye', 'fine','good','hello','morning')

To test these out, one can find the respective sign actions on google.

About

This is a project that applies an ASL translation filter over a virtual camera which can then be used in teleconferences such as zoom, discord and skype.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published