This item is only available for download by members of the University of Illinois community. Students, faculty, and staff at the U of I may log in with your NetID and password to view the item. If you are trying to access an Illinois-restricted dissertation or thesis, you can request a copy through your library's Inter-Library Loan office or purchase a copy directly from ProQuest.
Permalink
https://hdl.handle.net/2142/19663
Description
Title
Human face modeling, analysis and synthesis
Author(s)
Tang, Li-An
Issue Date
1996
Doctoral Committee Chair(s)
Huang, Thomas S.
Department of Study
Electrical and Computer Engineering
Discipline
Electrical Engineering
Degree Granting Institution
University of Illinois at Urbana-Champaign
Degree Name
Ph.D.
Degree Level
Dissertation
Keyword(s)
Engineering, Electronics and Electrical
Language
eng
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.
Use this login method if you
don't
have an
@illinois.edu
email address.
(Oops, I do have one)
IDEALS migrated to a new platform on June 23, 2022. If you created
your account prior to this date, you will have to reset your password
using the forgot-password link below.
