Deformable Shape Detection and Description via Model-Based Region Grouping.

Abstract

A method for deformable shape detection and recognition is described. Deformable shape templates are used to partition the image into a globally consistent interpretation, determined in part by the minimum description length principle. Statistical shape models enforce the prior probabilities on global, parametric deformations for each object class. Once trained, the system autonomously segments deformed shapes from the 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. The recovered shape models can be used directly in object recognition. Experiments with color imagery are reported.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Aug 01, 1999
Accession Number
ADA367013

Entities

People

  • Lifeng Liu
  • Stan Sclaroff

Organizations

  • Boston University

Tags

Communities of Interest

  • Autonomy

DTIC Thesaurus Topics

  • Algorithms
  • Computational Complexity
  • Computer Science
  • Computer Vision
  • Databases
  • Detection
  • Identification
  • Image Processing
  • Image Recognition
  • Image Segmentation
  • Models
  • Object Recognition
  • Pattern Recognition
  • Probability
  • Recognition
  • Statistical Shape Models
  • Template Patterns

Fields of Study

  • Physics

Readers

  • Artificial Intelligence
  • Structural Dynamics.
  • Vision Science/Vision Psychology/Cognitive Neuroscience.