Automatic Deformable Shape Segmentation for Image Database Search Applications.

Abstract

A method for shape based. image database indexing is described. Deformable shape templates are used to group color image regions into globally consistent configurations. A statistical shape model is used to enforce the prior probabilities on global, parametric deformations for each object class. The segmentation is determined in part by the minimum description length (MDL) principle. Once trained; the system autonomously segments deformed shapes from he background, while not merging them with adjacent objects or shadows. The formulation can be used to group image regions based on any image homogeneity predicate; e.g., texture, color, or motion. Preliminary experiments in color segmentation and shape-based retrieval are reported.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Aug 01, 1999
Accession Number
ADA366986

Entities

People

  • Lifeng Liu
  • Stan Sclaroff

Organizations

  • Boston University

Tags

Communities of Interest

  • Autonomy

DTIC Thesaurus Topics

  • Algorithms
  • Applied Computer Science
  • Aspect Ratio
  • Automatic
  • Computational Complexity
  • Computer Science
  • Computer Vision
  • Data Sets
  • Databases
  • Homogeneity
  • Image Processing
  • Image Segmentation
  • Models
  • Probability
  • Simplex Method
  • Statistical Shape Models
  • Template Patterns

Fields of Study

  • Physics

Readers

  • Fluid Dynamics.
  • Image Processing and Computer Vision.
  • Neural Network Machine Learning.