System and method for recognizing a 3-D object by generating a 2-D image of the object from a transformed 3-D model

• US 6,002,782 A
• Filed: 11/12/1997
• Issued: 12/14/1999
• Est. Priority Date: 11/12/1997
• Status: Expired due to Term

• Current Assignee: Unisys Corporation
• Original Assignee: Unisys Corporation
• Inventors: Dionysian, Raffi
• Primary Examiner(s): COUSO, YON JUNG
• Application Number:
  US08/968,019
• Time in Patent Office: 762 Days
• Field of Search: 382/115, 382/118, 382/154, 382/284, 704/273, 340/825.3, 340/825.31, 340/825.34, 902/3, 902/4, 902/25
• US Class Current: 382/118
• CPC Class Codes: G06V 10/32 Normalisation of the pattern dimensions
• CPC Class Codes: G06V 20/647 by matching two-dimensional images to three-dimensional objects
• CPC Class Codes: G06V 40/161 Detection; Localisation; Normalisation

Abstract

A method of electronically recognizing a three-dimensional object X includes an enrollment phase wherein a three-dimensional digital model of the surface of the object X is stored in a memory. Thereafter, in an access phase, a two-dimensional access image of an unidentified object is acquired by a camera which views the object from a particular direction which is unpredictable. Then, from the stored three-dimensional model, a two-dimensional image of the model is generated as seen from a selectable viewing direction which approximates the particular direction from which the unidentified object is viewed in the access image. Since the selectable viewing direction of the model approximates the direction in which the object is viewed by the camera, a correlation between the access image of the unidentified object and the image that is generated from the model is very high.

Claims

1. A method of electronically recognizing a three-dimensional object X;

said method including the steps of;

storing in a memory, a three-dimensional digital model of the surface of said object X;

acquiring a planar two-dimensional image of an unidentified object as viewed from an unpredictable direction;

automatically aligning said model to said unpredictable direction by transforming said model, without any manual input from an operator, until three predetermined points in the transformed model and three corresponding points in said two-dimensional image have substantially the same coordinates in the plane of said image;

generating, from said transformed three-dimensional model, a two-dimensional image of said model in said plane; and

,

identifying said unidentified object as said object X only if a correlation between said image of said unidentified object and said image of said model from said generating step exceeds a predetermined threshold.

3. A method according to claim 1 wherein said object X and said unidentified object are a human face.

4. A method according to claim 3 wherein said three predetermined points are the outside corners of two eyes on said face, and the center of a mouth on said face.

5. A method according to claim 3 wherein said three predetermined points are the outside corners of two eyes on said face, and the center of a chin on said face.

6. A method according to claim 3 wherein said three predetermined points are the outside corners of two eyes on said face and the tip of a nose on said face.

7. A method according to claim 3 wherein said three predetermined points are opposite points on the bridge of a nose on said face and the center of a mouth on said face.

8. A method according to claim 3 wherein said three-dimensional model includes a plurality of radiuses at respective angles θ

and φ

, each of which identifies a point on the surface of the model of said object X.

9. A method according to claim 3 wherein said three-dimensional model further includes a respective pixel value for multiple points on said surface of said face, and wherein said two-dimensional image of said model is obtained by projecting the pixel values onto said plane.

10. A method according to claim 3 wherein said two-dimensional image of said model is obtained by a) determining the angles between said unpredictable direction and respective vectors that extend perpendicularly from multiple points on the surface of said face, b) selecting a pixel value for each such point which increases as the corresponding angle decreases, and c) projecting the pixel values onto said plane.

11. A method according to claim 1 and further including the step of enabling said unidentified object to enter a secure area only if said correlation exceeds said predetermined threshold.

2. A system for electronically recognizing a three-dimensional object X;

said system being comprised of;

a memory which stores a three-dimensional model of the surface of said object X;

a camera which acquires a two-dimensional image of an unidentified object as viewed from an unpredictable direction;

an automatic alignment means which aligns said model to said unpredictable direction by transforming said model without any manual input from an operator, until three predetermined points in the transformed model and three corresponding points in said two-dimensional image have substantially the same coordinates in the plane of said image;

an image generating means for generating, from said transformed model, a two-dimensional image of said model in said plane; and

,

a correlating means, for identifying said unidentified object as said object X only if a correlation between said image of said unidentified object and said image of said model from said generating step exceeds a predetermined threshold.