Accession Number:

ADA459820

Title:

Dissociated Dipoles: Image Representation via Non-local Comparisons

Descriptive Note:

Corporate Author:

MASSACHUSETTS INST OF TECH CAMBRIDGE ARTIFICIAL INTELLIGENCE LAB

Personal Author(s):

Report Date:

2003-08-01

Pagination or Media Count:

16.0

Abstract:

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 filters 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 Dissociated Dipole, or Sticks 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.

Subject Categories:

  • Linguistics
  • Theoretical Mathematics
  • Electricity and Magnetism

Distribution Statement:

APPROVED FOR PUBLIC RELEASE