Retrieving Images by Appearance

Abstract

A system to retrieve images using a description of the image intensity surface is presented. Gaussian derivative filters at several scales are applied to the image and low order 2D differential invariants are computed. The resulting multi-scale representation is indexed for rapid retrieval. Queries are designed by the users from an example image by selecting appropriate regions. The invariant vectors corresponding to these regions are matched with the database counterparts both in feature and coordinate space. This yields a match score per image. Images are sorted by the match score and displayed. Experiments conducted with over 1500 images of objects embedded in arbitrary backgrounds are described. It is observed that images similar in appearance and whose viewpoint is within small view variations of the query can be retrieved with an average precision of 56%.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 1997
Accession Number
ADA331082

Entities

People

  • R. Manmatha
  • Sai Ravela

Organizations

  • University of Massachusetts Amherst

Tags

Communities of Interest

  • Air Platforms

DTIC Thesaurus Topics

  • Algorithms
  • Cameras
  • Computations
  • Computer Vision
  • Databases
  • Feature Extraction
  • Filters
  • Images
  • Intensity
  • Materials
  • Object Recognition
  • Precision
  • Recognition
  • Sampling
  • Three Dimensional
  • Two Dimensional
  • United States

Fields of Study

  • Computer science

Readers

  • Control Systems Engineering.
  • Human-Computer Interaction (HCI).
  • Regression Analysis.

Technology Areas

  • Space