Skip to content

Sign language recognition using leap motion controller using decision tree model. This hack is made during AUHack2017

License

Notifications You must be signed in to change notification settings

sbozhilov/sign-academy

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

32 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

sign-academy

Sign language alphabet intepreter.

This is a TypeScript framework that uses the Leap motion camera to interpret hand signs into sign language alphabet.The project was developed as our team's entry for the #AUHack2017 event. The framework uses the raw data provided by the camera and interprets the vector data into specific conditions that need to be fulfilled to obtain a specific letter.

For determining the letter symbol we have used the publication of Makiko Funasaka, Yu Ishikawa, Masami Takata, and Kazuki Joe Sign Language Recognition using Leap Motion Controller. Our prliminary KPI mesurments are positive, with accuracy around 67% far away from the 82% discribed in the publication.

To demonstrate the functionality the project has a simple Web UI that tests your ability to spell sign alphabet.

Devpost: link

Correct: alt text

Uncorrect: alt text

About

Sign language recognition using leap motion controller using decision tree model. This hack is made during AUHack2017

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 4

  •  
  •  
  •  
  •