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.
| Identifer | oai:union.ndltd.org:MIT/oai:dspace.mit.edu:1721.1/30398 |
| Date | 13 August 2003 |
| Creators | Balas, Benjamin J., Sinha, Pawan |
| Source Sets | M.I.T. Theses and Dissertation |
| Language | en_US |
| Detected Language | English |
| Format | 15 p., 18211324 bytes, 682491 bytes, application/postscript, application/pdf |
| Relation | Massachusetts Institute of Technology Computer Science and Artificial Intelligence Laboratory |
Page generated in 0.0016 seconds