A Biological-Plausable Architecture for Shape Recognition

Abstract

In this project, we explore a new approach to two-dimensional shape recognition. The method draws from literature on the Hough transform and its extensions. The methods is shown to be invariant to zoom, translation, rotation, and partial occlusion, although not zoom and partial occlusion simultaneously. The method is shown to be robust to distortions which smooth the contour shape (scale space changes). Furthermore, when the method misclassifies a shape, it chooses a shape which is most similar (in a human-intuitive sense) to the original. The method is developed and evaluated on a data base of tank silhouettes and a data base of fish silhouettes. The computer-based version of the algorithm is shown to have a reasonable implementation in neural hardware, and a neural-network implementation is described.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jun 30, 2006
Accession Number
ADA455395

Entities

People

  • Karthik Krish
  • Sanketh Shetty
  • Wesley Snyder

Organizations

  • North Carolina State University

Tags

Communities of Interest

  • C4I
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Algorithms
  • Artificial Intelligence
  • Center Of Gravity
  • Computer Vision
  • Data Sets
  • Databases
  • Delta Functions
  • Estimators
  • Fish
  • Network Architecture
  • Neural Networks
  • Neural Pathways
  • Object Recognition
  • Orientation (Direction)
  • Self Organizing Systems
  • Three Dimensional
  • Two Dimensional

Fields of Study

  • Computer science

Readers

  • Computer Vision.

Technology Areas

  • AI & ML
  • AI & ML - Machine Learning Algorithms
  • Space
  • Space - Spacecraft Maneuvers