DSpace Repository

Towards Man-Machine Interfaces: Combining Top-down Constraints with Bottom-up Learning in Facial Analysis

Show simple item record

dc.creator Kumar, Vinay P.
dc.date 2004-10-01T14:00:07Z
dc.date 2004-10-01T14:00:07Z
dc.date 2002-09-01
dc.date.accessioned 2013-10-09T02:40:09Z
dc.date.available 2013-10-09T02:40:09Z
dc.date.issued 2013-10-09
dc.identifier AITR-2002-008
dc.identifier CBCL-221
dc.identifier http://hdl.handle.net/1721.1/5569
dc.identifier.uri http://koha.mediu.edu.my:8181/xmlui/handle/1721
dc.description This thesis proposes a methodology for the design of man-machine interfaces by combining top-down and bottom-up processes in vision. From a computational perspective, we propose that the scientific-cognitive question of combining top-down and bottom-up knowledge is similar to the engineering question of labeling a training set in a supervised learning problem. We investigate these questions in the realm of facial analysis. We propose the use of a linear morphable model (LMM) for representing top-down structure and use it to model various facial variations such as mouth shapes and expression, the pose of faces and visual speech (visemes). We apply a supervised learning method based on support vector machine (SVM) regression for estimating the parameters of LMMs directly from pixel-based representations of faces. We combine these methods for designing new, more self-contained systems for recognizing facial expressions, estimating facial pose and for recognizing visemes.
dc.format 68 p.
dc.format 21293042 bytes
dc.format 2473001 bytes
dc.format application/postscript
dc.format application/pdf
dc.language en_US
dc.relation AITR-2002-008
dc.relation CBCL-221
dc.subject AI
dc.subject Facial Expression Recognition
dc.subject Pose Estimation
dc.subject Viseme Recognition
dc.subject SVM
dc.title Towards Man-Machine Interfaces: Combining Top-down Constraints with Bottom-up Learning in Facial Analysis


Files in this item

Files Size Format View

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record

Search DSpace


Advanced Search

Browse

My Account