Object Recognition By Alignment Using Invariant Projections of Planar Surfaces
In order to recognize an object in an image, we must determine the best transformation from object model to the image. In this paper, we show that for features from coplanar surfaces which undergo linear transformations in space, there exist projections invariant to the surface motions up to rotatio...
| Main Authors: | , |
|---|---|
| Language: | en_US |
| Published: |
2004
|
| Online Access: | http://hdl.handle.net/1721.1/6623 |
| _version_ | 1811069682031001600 |
|---|---|
| author | Nagao, Kanji Grimson W. Eric L. |
| author_facet | Nagao, Kanji Grimson W. Eric L. |
| author_sort | Nagao, Kanji |
| collection | MIT |
| description | In order to recognize an object in an image, we must determine the best transformation from object model to the image. In this paper, we show that for features from coplanar surfaces which undergo linear transformations in space, there exist projections invariant to the surface motions up to rotations in the image field. To use this property, we propose a new alignment approach to object recognition based on centroid alignment of corresponding feature groups. This method uses only a single pair of 2D model and data. Experimental results show the robustness of the proposed method against perturbations of feature positions. |
| first_indexed | 2024-09-23T08:14:19Z |
| id | mit-1721.1/6623 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T08:14:19Z |
| publishDate | 2004 |
| record_format | dspace |
| spelling | mit-1721.1/66232019-04-09T17:30:48Z Object Recognition By Alignment Using Invariant Projections of Planar Surfaces Nagao, Kanji Grimson W. Eric L. In order to recognize an object in an image, we must determine the best transformation from object model to the image. In this paper, we show that for features from coplanar surfaces which undergo linear transformations in space, there exist projections invariant to the surface motions up to rotations in the image field. To use this property, we propose a new alignment approach to object recognition based on centroid alignment of corresponding feature groups. This method uses only a single pair of 2D model and data. Experimental results show the robustness of the proposed method against perturbations of feature positions. 2004-10-08T20:34:39Z 2004-10-08T20:34:39Z 1994-02-01 AIM-1463 http://hdl.handle.net/1721.1/6623 en_US AIM-1463 214263 bytes 569720 bytes application/octet-stream application/pdf application/octet-stream application/pdf |
| spellingShingle | Nagao, Kanji Grimson W. Eric L. Object Recognition By Alignment Using Invariant Projections of Planar Surfaces |
| title | Object Recognition By Alignment Using Invariant Projections of Planar Surfaces |
| title_full | Object Recognition By Alignment Using Invariant Projections of Planar Surfaces |
| title_fullStr | Object Recognition By Alignment Using Invariant Projections of Planar Surfaces |
| title_full_unstemmed | Object Recognition By Alignment Using Invariant Projections of Planar Surfaces |
| title_short | Object Recognition By Alignment Using Invariant Projections of Planar Surfaces |
| title_sort | object recognition by alignment using invariant projections of planar surfaces |
| url | http://hdl.handle.net/1721.1/6623 |
| work_keys_str_mv | AT nagaokanji objectrecognitionbyalignmentusinginvariantprojectionsofplanarsurfaces AT grimsonwericl objectrecognitionbyalignmentusinginvariantprojectionsofplanarsurfaces |