Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/17607
Title: Facial expression recognition and tracking based on distributed locally linear embedding and expression motion energy
Authors: YANG YONG
Keywords: Face recognition, Facial expression recognition, Distributed Locally Linear Embedding (DLLE), Expression motion energy, Virtual expression animations
Issue Date: 4-Oct-2007
Source: YANG YONG (2007-10-04). Facial expression recognition and tracking based on distributed locally linear embedding and expression motion energy. ScholarBank@NUS Repository.
Abstract: This research aims to develop an automated and interactive computer vision system for human facial expression recognition and tracking based on the facial structure features and movement information. Our system utilizes a subset of Feature Points (FPs) for describing the facial expressions. An unsupervised learning algorithm, Distributed Locally Linear Embedding (DLLE), is proposed to recover the inherent properties of scattered data lying on a manifold embedded in high-dimensional input facial images. The selected person-dependent facial expression images in a video are classified using DLLE. We also incorporate facial expression motion energy to describe the facial muscle's tension for person-independent tracking. It takes advantage of the optical flow method which tracks the feature points' movement information. By further considering different expressions' temporal transition characteristics, we are able to pin-point the expressions with higher accuracy. A 3D realistic interactive head model is created to derive multiple virtual expression animations according to the recognition results.
URI: http://scholarbank.nus.edu.sg/handle/10635/17607
Appears in Collections:Master's Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
Thesis_Yang Yong.pdf3.92 MBAdobe PDF

OPEN

NoneView/Download

Page view(s)

255
checked on Jan 22, 2018

Download(s)

898
checked on Jan 22, 2018

Google ScholarTM

Check


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