L

Learn2Sign

Being able to recognize sign language is an interesting computer vision problem and can be extremely useful for interacting with deaf people to those who don’t know how to use ASL.

L

Learn2Sign

Being able to recognize sign language is an interesting computer vision problem and can be extremely useful for interacting with deaf people to those who don’t know how to use ASL.

The problem Learn2Sign solves

We created this application to help people better communicate with the deaf using sign language to better communicate so that they can express themselves, this application uses a image classifier from teachable machines, which is a Google API. It detect user's hand gestures and show the corresponding english alphabets (basically it converts ASL to english language).

Being able to recognize sign language is an interesting computer vision problem while simultaneously being extremely useful for deaf people to interact with people who don’t know how to understand American Sign Language (ASL).

Challenges we ran into

  • Creating a model with good acccuracy in a general setting.
  • Reverse engineering the Teachable Machine's Web Plugin snippet to aggregate data and then display the characters accordingly.
  • Integrating the model into our website.
  • Deploying the application.

Discussion