System and method for image attribute recording and analysis for biometric applications

• US 20030138134A1
• Filed: 01/22/2003
• Published: 07/24/2003
• Est. Priority Date: 01/22/2002
• Status: Active Grant

• Current Assignee: Photoinaphoto.com
• Original Assignee: Photoinaphoto.com
• Inventors: Petrich, David B.
• Granted Patent: US 7,653,219 B2
• Time in Patent Office: Days
• US Class Current: 382/118
• CPC Class Codes: G06T 7/507 from shading G06T7/586 takes precedence
• CPC Class Codes: G06T 7/80 Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
• CPC Class Codes: G06V 10/25 Determination of region of interest [ROI] or a volume of interest [VOI]
• CPC Class Codes: G06V 40/161 Detection; Localisation; Normalisation

Abstract

A system for recording and analyzing lighting attributes associated with a calibrated target device captured within an image to provide for enhanced object recognition within the captured image. A target device is used to provide lighting information relative to a subject within the image. The attributes allow the lighting conditions at the time of the image capture to be reconstructed. In addition, two or more target devices may be use to triangulate the position of a light source to any point within the captured image. Further, the lighting attributes may be used to create a contour mapping of the subject captured within the image.

Claims

1. A method for increasing the accuracy of recognition of an object within an image, comprising:

including a target device that is calibrated to predetermined properties within the image prior to capturing the image;

determining attributes associated with the target device;

associating the attributes of the target device with the object;

generating a contour mapping of the object using the attributes; and

associating the contour mapping with the image, such that the contour mapping uniquely identifies the object within the image.

2. The method of claim 1, wherein the target device is a spherical ball that is suspended within the image, such that the shading of the spherical ball denotes the location of a light source associated with the image.

3. The method of claim 1, wherein the target device is coated such that light measurements and ambient light are measurable according to the reflection from the surface of the target device.

4. The method of claim 1, further comprising including another target device within the image prior to capturing the image.

5. The method of claim 4, further comprising determining the attributes of both target devices to triangulate light position associated with a light source with respect to a selected point within the image.

6. The method of claim 1, wherein the image is captured for the purposes of providing identification of the object within the image.

7. The method of claim 1, wherein the object is a human subject'"'"'s face such that the contour mapping is a contour mapping of the human subject'"'"'s face.

8. The method of claim 7, wherein the contour mapping of the subject'"'"'s human face may be associated with the subject such that a facial fingerprint is provided for the human subject.

9. The method of claim 7, wherein the contour mapping may be associated with an identification card associated with the subject, wherein a mathematical representation of the contour mapping is embedded within the identification card.

10. The method of claim 7, wherein the contour mapping may be associated with an identification card associated with the subject, wherein a mathematical representation of the contour mapping is stored within a database for reference to the identification card.

11. The method of claim 1, further comprising comparing a mathematical representation of the contour mapping to mathematical representations of previously stored contour mappings to determine if the contour mapping matches a contour mapping previously stored.

12. The method of claim 1, wherein attributes associated with the target device include at least one of light direction, light diffusion, triangulation coordinates, camera angle, color, perspective, scale, and sizing.

18. The computer-readable medium of claim 1, wherein the attribute information stored within the index region include at least one of light direction, light diffusion, triangulation coordinates, camera angle, color, perspective, scale, and sizing.

13. A computer-readable medium having stored thereon a data structure, comprising:

data stored in an image region that includes digital information defining an image including a target device and an object; and

an index region that includes attribute information and a contour mapping of the object, wherein the attribute information describes attributes of the target device in the image and the contour mapping uniquely identifies the object within the image.

14. The computer-readable medium of claim 13, further comprising digital information stored in the image region that represents another target device within the image.

15. The computer-readable medium of claim 14, wherein the index region further comprises a triangulated light position measurement with respect to a selected point within the image, wherein the triangulated light position measurement corresponds to attribute information for both target devices within the image.

16. The computer-readable medium of claim 13, wherein the contour mapping may be associated with an identification card associated with the subject, wherein a mathematical representation of the contour mapping is one of stored within a database for reference to the identification card and embedded within the identification card.

17. The computer-readable medium of claim 13, further comprising comparing a mathematical representation of the contour mapping to mathematical representations of previously stored contour mappings to determine if the contour mapping matches a contour mapping previously stored.

19. A system for increasing the accuracy of recognition of an object within an image, comprising:

means for determining attributes associated with a target device that is calibrated to predetermined properties and included within the image prior to capturing the image;

means for associating the lighting attributes of the target device with the object;

means for generating a contour mapping of the object according using the lighting attributes; and

means for associating the contour mapping with the image, such that the contour mapping uniquely identifies the object within the image.

20. The system of claim 19, further comprising another target device within the image prior to capturing the image such that the attributes of both target devices allow a light direction associated with a selected point within the image to be triangulated.