Visual Distinctness Determined by Partially Invariant Features
Abstract
This paper describes a system for the automatically learned partitioning of "visual patterns" in digital images, based on a sophisticated, band-pass, filtering operation, with fixed scale and orientation sensitivity. The "visual patterns" are defined as the features which have the highest degree of alignment in the statistical structure across different frequency bands. Here we show a computational visual distinctness measure computed from the image representational model based on visual patterns. It is applied to quantify the visual distinctness of targets in complex natural scenes. We also investigate the relation between the computational distinctness measure and the visual target distinctness measured by human observers.
Document Details
- Document Type
- Technical Report
- Publication Date
- Mar 01, 2000
- Accession Number
- ADP010532
Entities
People
- J. A. Garcia
- J. Fdez-valdivia
- Rose Rodriquez-sanchez
- Xose R. Fdez-vidal
Organizations
- University of Granada