The Role of Knowledge in Visual Shape Representation
This report shows how knowledge about the visual world can be built into a shape representation in the form of a descriptive vocabulary making explicit the important geometrical relationships comprising objects' shapes. Two computational tools are offered: (1) Shapestokens are placed on a...
| Main Author: | |
|---|---|
| Language: | en_US |
| Published: |
2004
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/6833 |
| _version_ | 1811074706828165120 |
|---|---|
| author | Saund, Eric |
| author_facet | Saund, Eric |
| author_sort | Saund, Eric |
| collection | MIT |
| description | This report shows how knowledge about the visual world can be built into a shape representation in the form of a descriptive vocabulary making explicit the important geometrical relationships comprising objects' shapes. Two computational tools are offered: (1) Shapestokens are placed on a Scale-Space Blackboard, (2) Dimensionality-reduction captures deformation classes in configurations of tokens. Knowledge lies in the token types and deformation classes tailored to the constraints and regularities ofparticular shape worlds. A hierarchical shape vocabulary has been implemented supporting several later visual tasks in the two-dimensional shape domain of the dorsal fins of fishes. |
| first_indexed | 2024-09-23T09:54:05Z |
| id | mit-1721.1/6833 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T09:54:05Z |
| publishDate | 2004 |
| record_format | dspace |
| spelling | mit-1721.1/68332019-04-10T14:25:05Z The Role of Knowledge in Visual Shape Representation Saund, Eric shape representation dimensionality-reduction knowledge sscale-space later vision This report shows how knowledge about the visual world can be built into a shape representation in the form of a descriptive vocabulary making explicit the important geometrical relationships comprising objects' shapes. Two computational tools are offered: (1) Shapestokens are placed on a Scale-Space Blackboard, (2) Dimensionality-reduction captures deformation classes in configurations of tokens. Knowledge lies in the token types and deformation classes tailored to the constraints and regularities ofparticular shape worlds. A hierarchical shape vocabulary has been implemented supporting several later visual tasks in the two-dimensional shape domain of the dorsal fins of fishes. 2004-10-20T20:00:44Z 2004-10-20T20:00:44Z 1988-10-01 AITR-1092 http://hdl.handle.net/1721.1/6833 en_US AITR-1092 300 p. 38394678 bytes 31060480 bytes application/postscript application/pdf application/postscript application/pdf |
| spellingShingle | shape representation dimensionality-reduction knowledge sscale-space later vision Saund, Eric The Role of Knowledge in Visual Shape Representation |
| title | The Role of Knowledge in Visual Shape Representation |
| title_full | The Role of Knowledge in Visual Shape Representation |
| title_fullStr | The Role of Knowledge in Visual Shape Representation |
| title_full_unstemmed | The Role of Knowledge in Visual Shape Representation |
| title_short | The Role of Knowledge in Visual Shape Representation |
| title_sort | role of knowledge in visual shape representation |
| topic | shape representation dimensionality-reduction knowledge sscale-space later vision |
| url | http://hdl.handle.net/1721.1/6833 |
| work_keys_str_mv | AT saunderic theroleofknowledgeinvisualshaperepresentation AT saunderic roleofknowledgeinvisualshaperepresentation |