Deformable Prototypes for Encoding Shape Categories in Image Databases

Abstract

We describe a method for shape-based image database search that uses deformable prototypes to represent categories. Rather than directly comparing a candidate shape with all shape entries in the database, shapes are compared in terms of the types of nonrigid deformations (differences) that relate them to a small subset of representative prototypes. To solve the shape correspondence and alignment problem, we employ the technique of modal matching, an information-preserving shape decomposition for matching, describing, and comparing shapes despite sensor variations and nonrigid deformations. In modal matching, shape is decomposed into an ordered basis of orthogonal principal components. We demonstrate the utility of this approach for shape comparison in 2-D image databases.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 1997
Accession Number
ADA440107

Entities

People

  • Stan Sclaroff

Organizations

  • Boston University

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Algorithms
  • Coding
  • Computer Graphics
  • Computer Vision
  • Coordinate Systems
  • Databases
  • Equations
  • Fish
  • Frequency
  • Lagomorphs
  • Models
  • Pattern Recognition
  • Prototypes
  • Square Roots
  • Two Dimensional

Fields of Study

  • Physics

Readers

  • Computer Vision.