Gesture imitation using machine learning techniques

Itauma Isong Itauma*, Hasan Kivrak, Hatice Kose

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

18 Citations (Scopus)

Abstract

This study is a part of an ongoing project which aims to assist in teaching Sign Language (SL) to hearing-impaired children by means of non-verbal communication and imitation-based interaction games between a humanoid robot and a child. In this paper, the problem is geared towards a robot learning to imitate basic upper torso gestures (SL signs) using different machine learning techniques. RGBD sensor (Microsoft Kinect) is employed to track the skeletal model of humans and create a training set. A novel method called Decision Based Rule is proposed. Additionally, linear regression models are compared to find which learning technique has a higher accuracy on gesture prediction. The learning technique with the highest accuracy is then used to simulate an imitation system where the Nao robot imitates these learned gestures as observed by the users.

Original languageEnglish
Title of host publication2012 20th Signal Processing and Communications Applications Conference, SIU 2012, Proceedings
DOIs
Publication statusPublished - 2012
Event2012 20th Signal Processing and Communications Applications Conference, SIU 2012 - Fethiye, Mugla, Turkey
Duration: 18 Apr 201220 Apr 2012

Publication series

Name2012 20th Signal Processing and Communications Applications Conference, SIU 2012, Proceedings

Conference

Conference2012 20th Signal Processing and Communications Applications Conference, SIU 2012
Country/TerritoryTurkey
CityFethiye, Mugla
Period18/04/1220/04/12

Fingerprint

Dive into the research topics of 'Gesture imitation using machine learning techniques'. Together they form a unique fingerprint.

Cite this