Abstract

Most deaf children are born into hearing families and the majority do not begin their Sign Language learning before age 3-6 in school. As children learning Sign Language from infancy show higher language proficiency than those who do not, it underlines the importance of hearing parents learning how to sign. The recent innovation in the technology and introduction of new gesture control based devices, like leap motion controller. Technology that can track finger and hand gestures accurately at very low cost. The research method in Naïve Bayes algorithm, in order to classify 26 alphabet letter of Indonesian sign language including letter J and Z which using gesture for describe it. The Leap Motion controller is a consumer gesture sensor aimed to augment a user’s interactive experience with their computer and it was utilized as an interface for hand motion tracking without the need of wearing any external instruments. It use for derive feature data from the deaf children gesture recording to set data in application. The accuracy level of the test result reached 96%.

Highlights

  • Persons with disabilities are groups of limitation persons that can hinder their participation in community

  • The previous study by Wibowo et al [3] recognize 24 alpahbetic Indonesian letters in Indonesian sign language which resulted in average classfication accuracy for Naïve Bayes is 95%

  • Marin et al [5] investigated the performance of Leap Sensors Control by training Support Vector Machine (SVM) Classifier to recorgnize 10 different static mark with 1,400 sample counts capable of achieving an average accuracy of 80% as well as research focusing on challenges that include features for accurate signaling cues, and argues on how nomalization to accommodate a reliable system for users with different hand sizes

Read more

Summary

Introduction

Persons with disabilities are groups of limitation persons that can hinder their participation in community. The previous study by Wibowo et al [3] recognize 24 alpahbetic Indonesian letters in Indonesian sign language which resulted in average classfication accuracy for Naïve Bayes is 95%. Chen et al.[6] use the algorithm Hidden Markov Model (HMM) and Support Vector Machine (SVM) for dynamic hand movements. This study detect numbers and alphabets with a total of 36 movements captured by utilizing Leap Motion. Based on those issue above, an automated system that is usefull as a translation from sign language into written language is needed. The research is based on Classfier Algortihm and sensor Leap Motion Control (LMC), focused on the dynamic alphabet letters and words of Indonesian sign language (SIBI)

Leap Motion Control
Naïve Bayes Classfier
Data Acquistion
Desain System
Experiment
Findings
Result
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call