Boosting a Biologically Inspired Local Descriptor for Geometry-free Face and Full Multi-view 3D Object Recognition
Object recognition systems relying on local descriptors are increasingly used because of their perceived robustness with respect to occlusions and to global geometrical deformations. Descriptors of this type -- based on a set of oriented Gaussian derivative filters -- are used in our recognition sy...
| Main Authors: | , |
|---|---|
| Language: | en_US |
| Published: |
2005
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/30557 |
| _version_ | 1811072541010165760 |
|---|---|
| author | Yokono, Jerry Jun Poggio, Tomaso |
| author_facet | Yokono, Jerry Jun Poggio, Tomaso |
| author_sort | Yokono, Jerry Jun |
| collection | MIT |
| description | Object recognition systems relying on local descriptors are increasingly used because of their perceived robustness with respect to occlusions and to global geometrical deformations. Descriptors of this type -- based on a set of oriented Gaussian derivative filters -- are used in our recognition system. In this paper, we explore a multi-view 3D object recognition system that does not use explicit geometrical information. The basic idea is to find discriminant features to describe an object across different views. A boosting procedure is used to select features out of a large feature pool of local features collected from the positive training examples. We describe experiments on face images with excellent recognition rate. |
| first_indexed | 2024-09-23T09:07:33Z |
| id | mit-1721.1/30557 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T09:07:33Z |
| publishDate | 2005 |
| record_format | dspace |
| spelling | mit-1721.1/305572019-04-10T20:53:52Z Boosting a Biologically Inspired Local Descriptor for Geometry-free Face and Full Multi-view 3D Object Recognition Yokono, Jerry Jun Poggio, Tomaso AI 3D multiview object recognition SVM and boosting classifiers Object recognition systems relying on local descriptors are increasingly used because of their perceived robustness with respect to occlusions and to global geometrical deformations. Descriptors of this type -- based on a set of oriented Gaussian derivative filters -- are used in our recognition system. In this paper, we explore a multi-view 3D object recognition system that does not use explicit geometrical information. The basic idea is to find discriminant features to describe an object across different views. A boosting procedure is used to select features out of a large feature pool of local features collected from the positive training examples. We describe experiments on face images with excellent recognition rate. 2005-12-22T02:33:20Z 2005-12-22T02:33:20Z 2005-07-07 MIT-CSAIL-TR-2005-046 AIM-2005-023 CBCL-254 http://hdl.handle.net/1721.1/30557 en_US Massachusetts Institute of Technology Computer Science and Artificial Intelligence Laboratory 22 p. 49560015 bytes 7562398 bytes application/postscript application/pdf application/postscript application/pdf |
| spellingShingle | AI 3D multiview object recognition SVM and boosting classifiers Yokono, Jerry Jun Poggio, Tomaso Boosting a Biologically Inspired Local Descriptor for Geometry-free Face and Full Multi-view 3D Object Recognition |
| title | Boosting a Biologically Inspired Local Descriptor for Geometry-free Face and Full Multi-view 3D Object Recognition |
| title_full | Boosting a Biologically Inspired Local Descriptor for Geometry-free Face and Full Multi-view 3D Object Recognition |
| title_fullStr | Boosting a Biologically Inspired Local Descriptor for Geometry-free Face and Full Multi-view 3D Object Recognition |
| title_full_unstemmed | Boosting a Biologically Inspired Local Descriptor for Geometry-free Face and Full Multi-view 3D Object Recognition |
| title_short | Boosting a Biologically Inspired Local Descriptor for Geometry-free Face and Full Multi-view 3D Object Recognition |
| title_sort | boosting a biologically inspired local descriptor for geometry free face and full multi view 3d object recognition |
| topic | AI 3D multiview object recognition SVM and boosting classifiers |
| url | http://hdl.handle.net/1721.1/30557 |
| work_keys_str_mv | AT yokonojerryjun boostingabiologicallyinspiredlocaldescriptorforgeometryfreefaceandfullmultiview3dobjectrecognition AT poggiotomaso boostingabiologicallyinspiredlocaldescriptorforgeometryfreefaceandfullmultiview3dobjectrecognition |