Window-based method for approximating the Hausdorff in three-dimensional range imagery

DWPI Title: Three-dimensional range imagery method for facial recognition, involves determining that Hausdorff fraction exceeds threshold to determine whether three-dimensional image matches three-dimensional object
Abstract: One approach to pattern recognition is to use a template from a database of objects and match it to a probe image containing the unknown. Accordingly, the Hausdorff distance can be used to measure the similarity of two sets of points. In particular, the Hausdorff can measure the goodness of a match in the presence of occlusion, clutter, and noise. However, existing 3D algorithms for calculating the Hausdorff are computationally intensive, making them impractical for pattern recognition that requires scanning of large databases. The present invention is directed to a new method that can efficiently, in time and memory, compute the Hausdorff for 3D range imagery. The method uses a window-based approach.
Use: Method for three-dimensional (3D) range imagery for facial recognition.
Advantage: The method allows computing Hausdorff for three-dimensional range imagery in a time and memory efficient manner. The method allows easy generation of the three-dimensional range image.
Novelty: The method involves representing a set of coordinates of points in a window according to a distance kernel, and centering the window at an index of a probe range image to provide a set of coordinates of centered points for points of a template range image. Distance from a closest corresponding point to the centered points is determined. A determination is made that Hausdorff fraction exceeds a threshold to determine whether a three-dimensional image matches a three-dimensional object.
Filed: 9/29/2005
Application Number: US2005238609A
Tech ID: SD 7836.1
This invention was made with Government support under Contract No. DE-NA0003525 awarded by the United States Department of Energy/National Nuclear Security Administration. The Government has certain rights in the invention.
Data from Derwent World Patents Index, provided by Clarivate
All rights reserved. Republication or redistribution of Clarivate content, including by framing or similar means, is prohibited without the prior written consent of Clarivate. Clarivate and its logo, as well as all other trademarks used herein are trademarks of their respective owners and used under license.