Files in this item



application/pdf9702681.pdf (4MB)Restricted to U of Illinois
(no description provided)PDF


Title:Human face modeling, analysis and synthesis
Author(s):Tang, Li-An
Doctoral Committee Chair(s):Huang, Thomas S.
Department / Program:Electrical and Computer Engineering
Discipline:Electrical Engineering
Degree Granting Institution:University of Illinois at Urbana-Champaign
Subject(s):Engineering, Electronics and Electrical
Abstract:This thesis research deals with some general problems related to model-based coding systems. While we are looking for the solutions to individual problems, such as facial motion analysis and expression synthesis, we emphasize the importance of the automatic human face modeling algorithm, which is the basis of our model-based coding system. An automatic facial feature extraction algorithm is discussed in detail in this thesis. Based on template matching, the face area and the key points around each facial feature can be determined accurately on the front and side profile view face images. Then a realistic face model of a particular person can be created by mapping a generic 3-D face model to these feature points followed by texture mapping using the face images. A facial motion analysis scheme is used to obtain the motion parameters associated with the face model. Either two end frames or sequences of images of people showing facial expressions can be used to derive the motion parameters related to various facial expressions.
Natural and realistic facial expressions can be synthesized by deforming the face model using derived motion parameters. A whole sequence of facial expressions can be reconstructed using interpolation techniques.
Another topic in this thesis is the characterization of facial expressions. Some preliminary results of characterizing human smiles using the motion vectors around the mouth area show how people smile in different ways and how the smiles can be characterized from a large set of smile data.
Finally, this thesis discusses two potential applications: video compression and face recognition. Some preliminary results show that the model-based coding approach is quite promising for many different applications.
Issue Date:1996
Rights Information:Copyright 1996 Tang, Li-An
Date Available in IDEALS:2011-05-07
Identifier in Online Catalog:AAI9702681
OCLC Identifier:(UMI)AAI9702681

This item appears in the following Collection(s)

Item Statistics