A classification scheme is implemented using Ecole Centrale Paris's RFLib.
We used the Leap Motion Controller and it's respective API (https://developer.leapmotion.com/documentation/cpp/api/Leap_Classes.html) in order to accurately recognize and classify letters of the American Sign Language (ASL) alphabet.
Click on the link below for a video demo of our work:
For the purposes of this project, we did not include the letters 'J' and 'Z' because they are "dynamic", meaning that their sign language representation requires movement as opposed to the rest of the letters in the alphabet which are "static"
Our work has been accepted to ICIP 2017, which will take place September 17-20, 2017 in Beijing, China. Details can be found here