Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/15795
Title: Facial expression imitation for human robot interaction
Authors: WANG CHEN
Keywords: robot, facial recognition,nonlinear mass-spring, robot imitation
Issue Date: 18-Apr-2009
Source: WANG CHEN (2009-04-18). Facial expression imitation for human robot interaction. ScholarBank@NUS Repository.
Abstract: As social robots become more and more interactive and communicated, it is crucialthat they can understand, perceive and imitate the human emotions appropriatelyin the social environment. We propose an interactive system consisting of two keycomponents, facial expression recognition and robot imitation. Within the recentdecade, facial expression recognition has become a hot topic. But the existing 3Dface mesh for facial expression recognition is based on the assumption of linearmass-spring model which can not simulate the facial muscle movements e ectively.Thus in the system,a nonlinear mass-spring model is employed to simulate twentytwo facial muscles' tensions during facial expressions, and then the elastic forcesof these tensions are grouped into a vector which is used as the input for facialexpression recognition. The experimental results show that the nonlinear facialmass-spring model coupled with the MLPs classi er is e ective to recognize thefacial expressions. For the robot imitation, we introduce the mechanism of ourrobot on imitating the facial expressions. Experimental results of imitating facialexpressions demonstrate that our robot can imitate six kinds of facial expressionse ectively.
URI: http://scholarbank.nus.edu.sg/handle/10635/15795
Appears in Collections:Master's Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
Thesis_Master Engineering_Wang chen.pdf2.14 MBAdobe PDF

OPEN

NoneView/Download

Page view(s)

290
checked on Dec 11, 2017

Download(s)

257
checked on Dec 11, 2017

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.