Objective Functions for Feature Discrimination

Abstract

We propose and evaluate a class of objective functions that rank hypotheses for feature labels. Our approach takes into account the representation cost and quality of the shapes themselves, and balances the geometric requirements against the photometric evidence. This balance is essential for any system using Under constrained or generic feature models. We introduce examples of specific models allowing the actual computation of the terms in the objective function, and show how this framework leads naturally to control parameters that have a clear semantic meaning. We illustrate the properties of our objective functions on synthetic and real images.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
May 01, 1989
Accession Number
ADA460919

Entities

People

  • Andrew J. Hanson
  • Pascal Fua

Organizations

  • SRI International

Tags

DTIC Thesaurus Topics

  • Abstracts
  • Availability
  • Classification
  • Computations
  • Contracts
  • Discrimination
  • Hypotheses
  • Information Operations
  • Instructions
  • Monitoring
  • Organizational Structure
  • Security
  • Societies
  • Standards

Fields of Study

  • Computer science

Readers

  • Computational Modeling and Simulation
  • Computer Vision.
  • Theoretical Analysis.