Evaluation of sets of oriented and non-oriented receptive fields as local descriptors
Local descriptors are increasingly used for the task of object recognition because of their perceived robustness with respect to occlusions and to global geometrical deformations. We propose a performance criterion for a local descriptor based on the tradeoff between selectivity and invariance. In t...
| Main Authors: | , |
|---|---|
| Language: | en_US |
| Published: |
2004
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/7284 |
| _version_ | 1811096055591206912 |
|---|---|
| author | Yokono, Jerry Jun Poggio, Tomaso |
| author_facet | Yokono, Jerry Jun Poggio, Tomaso |
| author_sort | Yokono, Jerry Jun |
| collection | MIT |
| description | Local descriptors are increasingly used for the task of object recognition because of their perceived robustness with respect to occlusions and to global geometrical deformations. We propose a performance criterion for a local descriptor based on the tradeoff between selectivity and invariance. In this paper, we evaluate several local descriptors with respect to selectivity and invariance. The descriptors that we evaluated are Gaussian derivatives up to the third order, gray image patches, and Laplacian-based descriptors with either three scales or one scale filters. We compare selectivity and invariance to several affine changes such as rotation, scale, brightness, and viewpoint. Comparisons have been made keeping the dimensionality of the descriptors roughly constant. The overall results indicate a good performance by the descriptor based on a set of oriented Gaussian filters. It is interesting that oriented receptive fields similar to the Gaussian derivatives as well as receptive fields similar to the Laplacian are found in primate visual cortex. |
| first_indexed | 2024-09-23T16:37:38Z |
| id | mit-1721.1/7284 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T16:37:38Z |
| publishDate | 2004 |
| record_format | dspace |
| spelling | mit-1721.1/72842019-04-15T00:40:28Z Evaluation of sets of oriented and non-oriented receptive fields as local descriptors Yokono, Jerry Jun Poggio, Tomaso AI local descriptor steerable filter Gaussian derivatives selectivity invariance Local descriptors are increasingly used for the task of object recognition because of their perceived robustness with respect to occlusions and to global geometrical deformations. We propose a performance criterion for a local descriptor based on the tradeoff between selectivity and invariance. In this paper, we evaluate several local descriptors with respect to selectivity and invariance. The descriptors that we evaluated are Gaussian derivatives up to the third order, gray image patches, and Laplacian-based descriptors with either three scales or one scale filters. We compare selectivity and invariance to several affine changes such as rotation, scale, brightness, and viewpoint. Comparisons have been made keeping the dimensionality of the descriptors roughly constant. The overall results indicate a good performance by the descriptor based on a set of oriented Gaussian filters. It is interesting that oriented receptive fields similar to the Gaussian derivatives as well as receptive fields similar to the Laplacian are found in primate visual cortex. 2004-10-20T21:05:24Z 2004-10-20T21:05:24Z 2004-03-24 AIM-2004-007 CBCL-237 http://hdl.handle.net/1721.1/7284 en_US AIM-2004-007 CBCL-237 20 p. 3426196 bytes 1925439 bytes application/postscript application/pdf application/postscript application/pdf |
| spellingShingle | AI local descriptor steerable filter Gaussian derivatives selectivity invariance Yokono, Jerry Jun Poggio, Tomaso Evaluation of sets of oriented and non-oriented receptive fields as local descriptors |
| title | Evaluation of sets of oriented and non-oriented receptive fields as local descriptors |
| title_full | Evaluation of sets of oriented and non-oriented receptive fields as local descriptors |
| title_fullStr | Evaluation of sets of oriented and non-oriented receptive fields as local descriptors |
| title_full_unstemmed | Evaluation of sets of oriented and non-oriented receptive fields as local descriptors |
| title_short | Evaluation of sets of oriented and non-oriented receptive fields as local descriptors |
| title_sort | evaluation of sets of oriented and non oriented receptive fields as local descriptors |
| topic | AI local descriptor steerable filter Gaussian derivatives selectivity invariance |
| url | http://hdl.handle.net/1721.1/7284 |
| work_keys_str_mv | AT yokonojerryjun evaluationofsetsoforientedandnonorientedreceptivefieldsaslocaldescriptors AT poggiotomaso evaluationofsetsoforientedandnonorientedreceptivefieldsaslocaldescriptors |