Towards Man-Machine Interfaces: Combining Top-down Constraints with Bottom-up Learning in Facial Analysis
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 que...
| Main Author: | |
|---|---|
| Language: | en_US |
| Published: |
2004
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/5569 |
| _version_ | 1826196213886615552 |
|---|---|
| author | Kumar, Vinay P. |
| author_facet | Kumar, Vinay P. |
| author_sort | Kumar, Vinay P. |
| collection | MIT |
| 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. |
| first_indexed | 2024-09-23T10:23:00Z |
| id | mit-1721.1/5569 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T10:23:00Z |
| publishDate | 2004 |
| record_format | dspace |
| spelling | mit-1721.1/55692019-04-12T08:26:35Z Towards Man-Machine Interfaces: Combining Top-down Constraints with Bottom-up Learning in Facial Analysis Kumar, Vinay P. AI Facial Expression Recognition Pose Estimation Viseme Recognition SVM 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. 2004-10-01T14:00:07Z 2004-10-01T14:00:07Z 2002-09-01 AITR-2002-008 CBCL-221 http://hdl.handle.net/1721.1/5569 en_US AITR-2002-008 CBCL-221 68 p. 21293042 bytes 2473001 bytes application/postscript application/pdf application/postscript application/pdf |
| spellingShingle | AI Facial Expression Recognition Pose Estimation Viseme Recognition SVM Kumar, Vinay P. Towards Man-Machine Interfaces: Combining Top-down Constraints with Bottom-up Learning in Facial Analysis |
| title | Towards Man-Machine Interfaces: Combining Top-down Constraints with Bottom-up Learning in Facial Analysis |
| title_full | Towards Man-Machine Interfaces: Combining Top-down Constraints with Bottom-up Learning in Facial Analysis |
| title_fullStr | Towards Man-Machine Interfaces: Combining Top-down Constraints with Bottom-up Learning in Facial Analysis |
| title_full_unstemmed | Towards Man-Machine Interfaces: Combining Top-down Constraints with Bottom-up Learning in Facial Analysis |
| title_short | Towards Man-Machine Interfaces: Combining Top-down Constraints with Bottom-up Learning in Facial Analysis |
| title_sort | towards man machine interfaces combining top down constraints with bottom up learning in facial analysis |
| topic | AI Facial Expression Recognition Pose Estimation Viseme Recognition SVM |
| url | http://hdl.handle.net/1721.1/5569 |
| work_keys_str_mv | AT kumarvinayp towardsmanmachineinterfacescombiningtopdownconstraintswithbottomuplearninginfacialanalysis |