Hand Feature Learning For Hand Shape Recognition

Hand Feature Learning For Hand Shape Recognition

Sign Language is the main form of communication of the Deaf Community. The hearing impaired people can communicate between each other, but they are unable to have a proper relation with hearing population. Lack of sign language knowledge in our society and low number of sign language translators produce the need for automatized sign language recognition systems that would understand sign languages. 
This project focuses on hand shape classification using static hand images cropped from sign language videos. The main objective is to extract hand shape features from 2D hand images in order to classify static signs of the sign language. I used convolutional autoencoder for feature extraction and SVM for the classification for this purpose.

Project Poster: 

Project Members: 

Begun Unal

Project Advisor: 

Lale Akarun

Project Status: 

Project Year: 

  • Fall

Contact us

Department of Computer Engineering, Boğaziçi University,
34342 Bebek, Istanbul, Turkey

  • Phone: +90 212 359 45 23/24
  • Fax: +90 212 2872461

Connect with us

We're on Social Networks. Follow us & get in touch.