Skip to content

Recognition of hand gestures in 3D space using a single low resolution camera for converting American Sign Language into any spoken language.

Notifications You must be signed in to change notification settings

Gunnika/Sign_Language_Detector-PyTorch

Repository files navigation

Sign_Language_Detector-PyTorch

Recognition of hand gestures in 3D space using a single low resolution camera for converting American Sign Language into any spoken language.

Set Up Instructions

The requirements.txt file should list all Python libraries that your notebooks depend on, and they will be installed using:

pip install -r requirements.txt

To run the web application:

python app.py -i 0.0.0.0 -o 8080

It will run your app on http://localhost:8080/

Screenshots

H

H

A

A

Demo Video

https://youtu.be/70nmZY5ASvw

Inspiration

There are only 250 certified sign language interpreters in India, translating for a deaf population of between 1.8 million and 7 million.

percentage

We need to devise a solution that allows inclusion of the deaf and mute people in normal conversations. Our application allows any user to point the camera towards a mute person (with consent, ofcourse) and effectively understand what he/she's trying to say.

American Sign Language (ASL)

American Sign Language (ASL) is a visual language. With signing, the brain processes linguistic information through the eyes. The shape, placement, and movement of the hands, as well as facial expressions and body movements, all play important parts in conveying information. ASL

Dataset used

Sign Language MNIST (https://www.kaggle.com/datamunge/sign-language-mnist) Each training and test case represents a label (0-25) as a one-to-one map for each alphabetic letter A-Z (and no cases for 9=J or 25=Z because of gesture motions).

Working

steps

Autocompletion and Word Suggestion simplify and accelerate the process of information transmission. The user can select one out of the top 4 suggestions or keep making more gestures until the desired word is obtained.

Use Cases

  1. Deaf people can have a common classroom by asking their questions/doubts without any hesitation
  2. Inclusion of this community in normal schools.
  3. Tourist Guides can communicate better using sign language

About

Recognition of hand gestures in 3D space using a single low resolution camera for converting American Sign Language into any spoken language.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published