Learning Shape Descriptions: Generating and Generalizing Models of Visual Objects
We present the results of an implemented system for learning structural prototypes from grey-scale images. We show how to divide an object into subparts and how to encode the properties of these subparts and the relations between them. We discuss the importance of hierarchy and grouping in rep...
| Main Author: | |
|---|---|
| Language: | en_US |
| Published: |
2004
|
| Online Access: | http://hdl.handle.net/1721.1/6870 |
| _version_ | 1826209863425851392 |
|---|---|
| author | Connell, Jonathan Hudson |
| author_facet | Connell, Jonathan Hudson |
| author_sort | Connell, Jonathan Hudson |
| collection | MIT |
| description | We present the results of an implemented system for learning structural prototypes from grey-scale images. We show how to divide an object into subparts and how to encode the properties of these subparts and the relations between them. We discuss the importance of hierarchy and grouping in representing objects and show how a notion of visual similarities can be embedded in the description language. Finally we exhibit a learning algorithm that forms class models from the descriptions produced and uses these models to recognize new members of the class. |
| first_indexed | 2024-09-23T14:33:15Z |
| id | mit-1721.1/6870 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T14:33:15Z |
| publishDate | 2004 |
| record_format | dspace |
| spelling | mit-1721.1/68702019-04-12T08:32:42Z Learning Shape Descriptions: Generating and Generalizing Models of Visual Objects Connell, Jonathan Hudson We present the results of an implemented system for learning structural prototypes from grey-scale images. We show how to divide an object into subparts and how to encode the properties of these subparts and the relations between them. We discuss the importance of hierarchy and grouping in representing objects and show how a notion of visual similarities can be embedded in the description language. Finally we exhibit a learning algorithm that forms class models from the descriptions produced and uses these models to recognize new members of the class. 2004-10-20T20:03:37Z 2004-10-20T20:03:37Z 1985-09-01 AITR-853 http://hdl.handle.net/1721.1/6870 en_US AITR-853 101 p. 10686540 bytes 4012801 bytes application/postscript application/pdf application/postscript application/pdf |
| spellingShingle | Connell, Jonathan Hudson Learning Shape Descriptions: Generating and Generalizing Models of Visual Objects |
| title | Learning Shape Descriptions: Generating and Generalizing Models of Visual Objects |
| title_full | Learning Shape Descriptions: Generating and Generalizing Models of Visual Objects |
| title_fullStr | Learning Shape Descriptions: Generating and Generalizing Models of Visual Objects |
| title_full_unstemmed | Learning Shape Descriptions: Generating and Generalizing Models of Visual Objects |
| title_short | Learning Shape Descriptions: Generating and Generalizing Models of Visual Objects |
| title_sort | learning shape descriptions generating and generalizing models of visual objects |
| url | http://hdl.handle.net/1721.1/6870 |
| work_keys_str_mv | AT connelljonathanhudson learningshapedescriptionsgeneratingandgeneralizingmodelsofvisualobjects |