2026-09-19T10:28:57Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/292432026-06-16T18:16:57Zcom_1721.1_7582com_1721.1_7581col_1721.1_131022
Tomaso Poggio.
Kumar, Vinay P. (Vinay Prasanna), 1972-
Massachusetts Institute of Technology. Dept. of Brain and Cognitive Sciences.
Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences
2005-10-14T19:24:06Z
2005-10-14T19:24:06Z
2002
2002
http://hdl.handle.net/1721.1/29243
51641245
Thesis (Ph.D. in Computational Cognitive Science)--Massachusetts Institute of Technology, Dept. of Brain and Cognitive Sciences, 2002.
Includes bibliographical references (leaves 72-[77]).
This thesis proposes a miethodology 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.
by Vinay P. Kumar.
Ph.D. in Computational Cognitive Science
72, [5] leaves
3717108 bytes
3716915 bytes
application/pdf
application/pdf
eng
Massachusetts Institute of Technology
M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission.
http://dspace.mit.edu/handle/1721.1/7582
Brain and Cognitive Sciences.
Towards trainable man-machine interfaces : combining top-down constraints with bottom-up learning in facial analysis
Towards man-machine interfaces : combining top-down constraints with bottom-up learning
Thesis
application/pdf
false
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="7d52f7ec-9894-41d3-a460-7f06ffb4bc82">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Language>eng</Language>
<Title>Towards trainable man-machine interfaces : combining top-down constraints with bottom-up learning in facial analysis</Title>
<Subtitle>Towards man-machine interfaces : combining top-down constraints with bottom-up learning</Subtitle>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2002</PublicationDate>
<Authors>
<Author>
<DisplayName>Kumar, Vinay P. (Vinay Prasanna), 1972-</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>http://dspace.mit.edu/handle/1721.1/7582</License>
<Keyword>Brain and Cognitive Sciences.</Keyword>
<Abstract>This thesis proposes a miethodology 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.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>