Department of 
Computer Science

Search our Site

Line

Back to Main Patents Page

  United States Patent
Image Object Matching Using Core Analysis and Deformable Shape Loci

Patent Number: 5,926,568
Date of Patent: 20 July 1999
Inventors: Edward L. Chaney, (Efland, N.C.); Daniel S. Fritsch (Chapel Hill, N.C.), Stephen M. Pizer (Chapel Hill, N.C.), Valen Johnson (Durham, N.C.), Alyson G. Wilson (Las Cruces, N.M.)
Assignee: The University of North Carolina at Chapel Hill, Chapel Hill, N.C.; Duke University, Durham, N.C.
Appl. No.: 885,330
Filed: June 30, 1997
Int. Cl.: G06K 009/64; G06K 009/68
U.S. Cl.: 382/217; 382/128; 382/203
31 Claims

Abstract
Methods, systems, and computer program products are provided for automatic image recognition of standard shapes which include a core-based deformable loci skeletal grid used to define and represent an object via a model template. The template includes deformable segments, the changes of which are measurable against the deformed model corresponding to an object in a subsequent image. Statistical correlation techniques optimize the match to further refine the shape of the subsequent image.

Horizontal Line
Department of Computer Science
Campus Box 3175, Sitterson Hall
College of Arts & Sciences
The University of North Carolina at Chapel Hill
Chapel Hill, NC 27599-3175 USA
Phone: (919) 962-1700
Fax: (919) 962-1799

Content Manager: pubs@cs.unc.edu
Server Manager: webmaster@cs.unc.edu
Last Content Review: 11 March 2001