Segmentation and Aggregation: An Approach to Figure-Ground Phenomena,

Abstract

We describe a new approach to low-level vision in which the task of image segmentation is to distinguish meaningful relationships between image elements from a background distribution of random alignments. Unlike most previous approaches, which start from idealized models of what we wish to detect in the world, this approach is not based on prior world knowledge and uses measurements which can be computed directly from the input signal. Groupings of image elements are formed over a wide range of sizes and classes while attempting to make use of all available statistical information at each level of the grouping hierarchy, resulting in far more sensitive discrimination than is possible from just local measurements. This paper explores the range of grouping capabilities and discrimination exhibited by the human visual system and discusses the application of the meaningfulness measure to each of them. (Author)

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 1982
Accession Number
ADP000123

Entities

People

  • David G. Lowe
  • Thomas O. Binford

Organizations

  • Stanford University

Tags

DTIC Thesaurus Topics

  • Computer Vision
  • Discrimination
  • Hierarchies
  • Image Segmentation
  • Measurement
  • Workshops

Fields of Study

  • Computer science

Readers

  • Computer Vision.
  • Theoretical Analysis.