Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
Dynamic System Design for American Sign Language Recognition
 

Summary: Dynamic System Design for American Sign Language
Recognition
Joe Naoum-Sawaya, Mazen Slim, Sami Khawam and Mohamad Adnan Al-Alaoui
Electrical and Computer Engineering Department.
American University of Beirut
Beirut, Lebanon
Email: {joe.sawaya@gmail.com, mazenslim@gmail.com, sami.khawam@gmail.com, adnan@aub.edu.lb}
Abstract In this paper, we present a real time system
for recognizing isolated and sentence American Sign Lan-
guage (ASL) gestures. We mainly focus on image preproc-
essing to isolate hand pose and motion which allow fast
and accurate recognition. Preprocessing is accomplished
through a series of adaptive modules forming a very adap-
tive system. Such a system achieved high accuracy rate
even with a noncomplex gesture recognition technique.
This evaluation was conducted using a set of 5 gestures
and translation in 4 different directions.
Keywords
Sign Language, Static and Dynamic Gesture Recogni-
tion, Motion Analysis, Pattern Analysis, Template

  

Source: Al-Alaoui, Mohamad Adnan - Faculty of Engineering and Architecture, American University of Beirut, Lebanon

 

Collections: Engineering