Data and Model-Driven Selection Using Color Regions
A key problem in model-based object recognition is selection, namely, the problem of determining which regions in the image are likely to come from a single object. In this paper we present an approach that extracts and uses color region information to perform selection either based solely on...
| Main Author: | |
|---|---|
| Language: | en_US |
| Published: |
2004
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/5994 |
| _version_ | 1826194621699457024 |
|---|---|
| author | Syeda-Mahmood, Tanveer Fathima |
| author_facet | Syeda-Mahmood, Tanveer Fathima |
| author_sort | Syeda-Mahmood, Tanveer Fathima |
| collection | MIT |
| description | A key problem in model-based object recognition is selection, namely, the problem of determining which regions in the image are likely to come from a single object. In this paper we present an approach that extracts and uses color region information to perform selection either based solely on image- data (data-driven), or based on the knowledge of the color description of the model (model -driven). The paper presents a method of perceptual color specification by color categories to extract perceptual color regions. It also discusses the utility of color-based selection in reducing the search involved in recognition. |
| first_indexed | 2024-09-23T09:58:46Z |
| id | mit-1721.1/5994 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T09:58:46Z |
| publishDate | 2004 |
| record_format | dspace |
| spelling | mit-1721.1/59942019-04-12T08:28:23Z Data and Model-Driven Selection Using Color Regions Syeda-Mahmood, Tanveer Fathima selection color recognition saliency visual attention sregion segmentation A key problem in model-based object recognition is selection, namely, the problem of determining which regions in the image are likely to come from a single object. In this paper we present an approach that extracts and uses color region information to perform selection either based solely on image- data (data-driven), or based on the knowledge of the color description of the model (model -driven). The paper presents a method of perceptual color specification by color categories to extract perceptual color regions. It also discusses the utility of color-based selection in reducing the search involved in recognition. 2004-10-04T14:25:38Z 2004-10-04T14:25:38Z 1992-02-01 AIM-1270 http://hdl.handle.net/1721.1/5994 en_US AIM-1270 29 p. 4497036 bytes 1782485 bytes application/postscript application/pdf application/postscript application/pdf |
| spellingShingle | selection color recognition saliency visual attention sregion segmentation Syeda-Mahmood, Tanveer Fathima Data and Model-Driven Selection Using Color Regions |
| title | Data and Model-Driven Selection Using Color Regions |
| title_full | Data and Model-Driven Selection Using Color Regions |
| title_fullStr | Data and Model-Driven Selection Using Color Regions |
| title_full_unstemmed | Data and Model-Driven Selection Using Color Regions |
| title_short | Data and Model-Driven Selection Using Color Regions |
| title_sort | data and model driven selection using color regions |
| topic | selection color recognition saliency visual attention sregion segmentation |
| url | http://hdl.handle.net/1721.1/5994 |
| work_keys_str_mv | AT syedamahmoodtanveerfathima dataandmodeldrivenselectionusingcolorregions |