Three-dimensional face recognition

• US 6,947,579 B2
• Filed: 10/31/2002
• Issued: 09/20/2005
• Est. Priority Date: 10/07/2002
• Status: Expired due to Term

• Current Assignee: Intel Benelux B. V.
• Original Assignee: TECHNION RESEARCH AND DEVELOPMENT FOUNDATION, LTD. (Technion-Israel Institute Of Technology)
• Inventors: Bronstein, Michael, Bronstein, Alexander, Kimmel, Ron
• Primary Examiner(s): Mehta, Bhavesh M.
• Assistant Examiner(s): DESIRE, GREGORY M
• Application Number:
  US10/284,281
• Publication Number:
  US 20040076313A1
• Time in Patent Office: 1,055 Days
• Field of Search: 345/419, 345/420, 345/428, 345/441, 382/118, 382/225, 382/274, 382/299
• US Class Current: 382/118
• CPC Class Codes: G01S 17/89 for mapping or imaging
• CPC Class Codes: G06T 17/00 Three dimensional [3D] modelling, e.g. data description of 3D objects
• CPC Class Codes: G06V 20/653 by matching three-dimensional models, e.g. conformal mapping of Riemann surfaces
• CPC Class Codes: G06V 40/172 Classification, e.g. identification

Abstract

Apparatus for obtaining 3-Dimensional data of a geometric body for matching, and particularly for use in facial matching, comprises a three dimensional scanner for obtaining three-dimensional topographical data of the body, a triangulator for receiving or forming said data into a triangulated manifold, a geodesic converter, for converting the triangulated manifold into a series of geodesic distances between pairs of points of the manifold, and a multi-dimensional scaler, for forming a low dimensional Euclidean representation of the series of geodesic distances, to give a bending invariant representation of the geometric body. In one variant, matching is carried out by taking the principle eigenvalues from the representation and plotting as co-ordinates in a feature space. Tilted or different expression versions of the same face tend to form clusters in the feature space allowing for matching. The apparatus preferably uses the fast marching method for the triangulated domain to obtain the geodesic distances.

Claims

1. Apparatus for matching between geometric bodies based on 3-dimensional data comprising:

an input for receiving representations of geometric bodies as Euclidean representations of sets of geodesic distances between sampled points of a triangulated manifold, said Euclidean representations being substantially bending invariant representations,

a distance calculator for calculating distances between respective geometric bodies based on said Euclidean representation, wherein said distance calculator comprises;

an eigenvalue extractor for extracting a predetermined number of eigenvalues from said Euclidean representations, and

a plotter for plotting said predetermined number of eigenvalues as a point on a feature space having a dimension for each of said predetermined number of Eigenvalues, and

a thresholder for thresholding a calculated distance to determine the presence or absence of a match wherein said thresholder is configured to be sensitive to clustering within said feature space.

2. Apparatus according to claim 1, wherein said predetermined number is three.

3. Apparatus according to claim 1, wherein said Euclidean representation is based upon geodesic distances between a sub-sampling of points of said triangulated manifold.

4. Apparatus according to claim 1, wherein said geometric body is a face, having soft geometric regions, being regions susceptible to short term geometric change and hard geometric regions, being regions substantially unsusceptible to short term geometric changes, and wherein said Euclidean representation is substantially limited to said hard geometric regions.

5. Apparatus according to claim 1, wherein said distance calculator is configured to use the Hausdorff metric.

6. Apparatus for obtaining 3-Dimensional data of geometric body for matching, and using said data to carry out matching between different bodies, said apparatus comprising:

a three dimensional scanner for obtaining three-dimensional topographical data of said body,

a triangulator for receiving said three-dimensional topographical data of said geometrc body and forming said data into a triangulated manifold,

a geodesic converter, connected subsequently to said triangulator, for converting said triangulated manifold into a series of geodesic distances between pairs of points of said manifold,

a bending invariant multi-dimensional scalar, connected subsequently to said geodesic converter, for forming a bending invariant low dimensional Euclidean representation of said series of geodesic distances, said low dimensional Euclidean representation providing a bending invariant representation of said geometric body,

a distance calculator, connected subsequently to said bending invariant multi-dimensional scalar, for calculating distances between geometric bodies based on said Euclidean representation, said distance calculator comprises;

an eigenvalue extractor for extracting a predetermined number of eigenvalues from said Euclidean representations, and

a plotter for plotting said predetermined number of Eigenvalues as a point on a feature space having a dimension for each of said predetermined number of eigenvalues, and

a thresholder, connected subsequently to said distance calculator, for thresholding a calculated distance to determine the presence or absence of a match, said thresholder is configured to be sensitive to clustering within said feature space, thereby to determine said presence or absence of said match.

7. Apparatus according to claim 6, wherein said predetermined number is three.

8. Apparatus according to claim 6, wherein said predetermined number is greater than three.