Dissociated Dipoles: Image representation via non-local comparisons
A fundamental question in visual neuroscience is how to represent image structure. The most common representational schemes rely on differential operators that compare adjacent image regions. While well-suited to encoding local relationships, such operators have significant drawbacks. Specifically,...
| Main Authors: | , |
|---|---|
| Language: | en_US |
| Published: |
2005
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/30398 |
| _version_ | 1811081190405308416 |
|---|---|
| author | Balas, Benjamin J. Sinha, Pawan |
| author_facet | Balas, Benjamin J. Sinha, Pawan |
| author_sort | Balas, Benjamin J. |
| collection | MIT |
| description | A fundamental question in visual neuroscience is how to represent image structure. The most common representational schemes rely on differential operators that compare adjacent image regions. While well-suited to encoding local relationships, such operators have significant drawbacks. Specifically, each filterÂs span is confounded with the size of its sub-fields, making it difficult to compare small regions across large distances. We find that such long-distance comparisons are more tolerant to common image transformations than purely local ones, suggesting they may provide a useful vocabulary for image encoding. .We introduce the ÂDissociated Dipole, or ÂSticks operator, for encoding non-local image relationships. This operator de-couples filter span from sub-field size, enabling parametric movement between edge and region-based representation modes. We report on the perceptual plausibility of the operator, and the computational advantages of non-local encoding. Our results suggest that non-local encoding may be an effective scheme for representing image structure. |
| first_indexed | 2024-09-23T11:42:52Z |
| id | mit-1721.1/30398 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T11:42:52Z |
| publishDate | 2005 |
| record_format | dspace |
| spelling | mit-1721.1/303982019-04-12T08:26:00Z Dissociated Dipoles: Image representation via non-local comparisons Balas, Benjamin J. Sinha, Pawan AI image representation recognition non-local filtering A fundamental question in visual neuroscience is how to represent image structure. The most common representational schemes rely on differential operators that compare adjacent image regions. While well-suited to encoding local relationships, such operators have significant drawbacks. Specifically, each filterÂs span is confounded with the size of its sub-fields, making it difficult to compare small regions across large distances. We find that such long-distance comparisons are more tolerant to common image transformations than purely local ones, suggesting they may provide a useful vocabulary for image encoding. .We introduce the ÂDissociated Dipole, or ÂSticks operator, for encoding non-local image relationships. This operator de-couples filter span from sub-field size, enabling parametric movement between edge and region-based representation modes. We report on the perceptual plausibility of the operator, and the computational advantages of non-local encoding. Our results suggest that non-local encoding may be an effective scheme for representing image structure. 2005-12-19T22:36:12Z 2005-12-19T22:36:12Z 2003-08-13 MIT-CSAIL-TR-2003-011 AIM-2003-018 CBCL-229 http://hdl.handle.net/1721.1/30398 en_US Massachusetts Institute of Technology Computer Science and Artificial Intelligence Laboratory 15 p. 18211324 bytes 682491 bytes application/postscript application/pdf application/postscript application/pdf |
| spellingShingle | AI image representation recognition non-local filtering Balas, Benjamin J. Sinha, Pawan Dissociated Dipoles: Image representation via non-local comparisons |
| title | Dissociated Dipoles: Image representation via non-local comparisons |
| title_full | Dissociated Dipoles: Image representation via non-local comparisons |
| title_fullStr | Dissociated Dipoles: Image representation via non-local comparisons |
| title_full_unstemmed | Dissociated Dipoles: Image representation via non-local comparisons |
| title_short | Dissociated Dipoles: Image representation via non-local comparisons |
| title_sort | dissociated dipoles image representation via non local comparisons |
| topic | AI image representation recognition non-local filtering |
| url | http://hdl.handle.net/1721.1/30398 |
| work_keys_str_mv | AT balasbenjaminj dissociateddipolesimagerepresentationvianonlocalcomparisons AT sinhapawan dissociateddipolesimagerepresentationvianonlocalcomparisons |