Use of an intrinsic image in face recognition

• US 8,194,975 B2
• Filed: 06/29/2009
• Issued: 06/05/2012
• Est. Priority Date: 06/29/2009
• Status: Active Grant

• Current Assignee: Innovation Asset Collective
• Original Assignee: Tandent Vision Science, Inc.
• Inventors: Smith, Casey Arthur
• Primary Examiner(s): Liu, Li
• Application Number:
  US12/459,238
• Publication Number:
  US 20100329546A1
• Time in Patent Office: 1,072 Days
• Field of Search: None
• US Class Current: 382/164
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 2207/30201 Face
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/90 Determination of colour characteristics
• CPC Class Codes: G06V 10/60 relating to illumination properties, e.g. using a reflectance or lighting model
• CPC Class Codes: G06V 2201/11 Technique with transformation invariance effect
• CPC Class Codes: G06V 40/16 Human faces, e.g. facial parts, sketches or expressions

Abstract

In an exemplary embodiment of the present invention, an automated, computerized method is provided for processing an image. According to a feature of the present invention, the method comprises the steps of providing an image file depicting an image, in a computer memory, identifying information in the image file relevant to a logical deduction regarding material and illumination aspects of an image and selected from information relevant to spatio-spectral aspects of an image and constituents of color; defining a constraint as a function of the information; and utilizing the constraint in an image segregation operation.

Claims

1. An automated, computerized method for processing an image, comprising the steps of:

providing an image file depicting the image, in a computer memory;

identifying information in the image file relevant to a logical deduction regarding material and illumination aspects of the image, the information being based upon spatio-spectral aspects of the image and constituents of color depicted in the image;

defining a constraint as a function of the information, wherein the constraint comprises a constraint based upon a tone mapping of the image expressed by log t_R +log t_G +log t_B =V, where t_R is an average for a red channel of material for pixels of a token t, t_G is an average for a green channel of material for pixels of the token t, t_B is an average for material for a blue channel of pixels of the token t, and where V is an average for a calculated intensity value for the token t, derived from the tone mapping; and

utilizing the constraint in an image segregation operation.

2. The method of claim 1 wherein the spatio-spectral aspects of the image comprises spatio-spectral operators.

3. The method of claim 1 wherein the constituents of color include intensity and chromaticity.

4. The method of claim 1 wherein the constraint is arranged to preserve shading contributing to an appearance of curvature of features depicted in the image, and to reduce shadowing effects.

5. The method of claim 1 wherein the constraint includes a second constraint based upon a chromaticity aspect of color depicted in the image.

6. An automated, computerized method for processing an image, comprising the steps of:

providing an image file depicting the image, in a computer memory;

organizing information for the image file relevant to a logical deduction regarding material and illumination aspects of the image, the information being based upon spatio-spectral aspects of the image and constituents of color depicted in the image, in a matrix equation expressed by;

[A] [x]=[b], wherein [A] expresses values determined by a constraining relationship imposed upon the information relevant to a logical deduction regarding material and illumination aspects of the image, [b] expresses information obtained from the image file, in the computer memory, and [x] expresses an unknown material/illumination component of the image; and

utilizing the matrix equation in an image segregation operation.

7. The method of claim 6 wherein the spatio-spectral aspects of the image comprises spatio-spectral operators.

8. The method of claim 6 wherein the constraining relationship is arranged to preserve shading contributing to an appearance of curvature of features depicted in the image, and to reduce shadowing effects.

9. A computer system which comprises:

a CPU; and

a memory storing an image file defining an image;

the CPU being arranged and configured to execute a routine to identify information in the image file relevant to a logical deduction regarding material and illumination aspects of the image, the information being based upon spatio-spectral aspects of the image and constituents of color depicted in the image, define a constraint as a function of the information, wherein the constraint comprises a constraint based upon a tone mapping of the image expressed by log t_R +log t_G +log t_B =V, where t_R is an average for a red channel of material for pixels of a token t, t_G is an average for a green channel of material for pixels of the token t, t_B is an average for material for a blue channel of pixels of the token t, and where V is an average for a calculated intensity value for the token t, derived from the tone mapping, and utilize the constraint in an image segregation operation.

10. A computer system which comprises:

a CPU; and

a memory storing an image file defining an image;

the CPU being arranged and configured to execute a routine to organize information for the image file relevant to a logical deduction regarding material and illumination aspects of the image, the information being based upon spatio-spectral aspects of the image and constituents of color depicted in the image, in a matrix equation expressed by;

[A] [x]=[b], wherein [A] expresses values determined by a constraining relationship imposed upon the information relevant to a logical deduction regarding material and illumination aspects of the image, [b] expresses information obtained from the image file, in the computer memory, and [x] expresses an unknown material/illumination component of the image and utilize the matrix equation in an image segregation operation.

11. A computer program product, disposed on a computer readable media, the product including computer executable process steps operable to control a computer to:

provide an image file depicting an image, in a computer memory;

identify information in the image file relevant to a logical deduction regarding material and illumination aspects of the image, the information being based upon spatio-spectral aspects of the image and constituents of color depicted in the image;

define a constraint as a function of the information, wherein the constraint comprises a constraint based upon a tone mapping of the image expressed by log t_R +log t_G +log t_B =V, where t_R is an average for a red channel of material for pixels of a token t, t_G is an average for a green channel of material for pixels of the token t, t_B is an average for material for a blue channel of pixels of the token t, and where V is an average for a calculated intensity value for the token t, derived from the tone mapping; and

utilize the constraint in an image segregation operation.

12. The computer program product of claim 11 wherein the spatio-spectral aspects of the image comprises spatio-spectral operators.

13. The computer program product of claim 11 wherein the constituents of color include intensity and chromaticity.

14. The computer program product of claim 11 wherein the constraint is arranged to preserve shading contributing to an appearance of curvature of features depicted in the image, and to reduce shadowing effects.

15. The computer program product of claim 11 wherein the constraint includes a second constraint based upon a chromaticity aspect of color depicted in the image.

16. A computer program product, disposed on a computer readable media, the product including computer executable process steps operable to control a computer to:

provide an image file depicting an image, in a computer memory;

organize information for the image file relevant to a logical deduction regarding material and illumination aspects of the image, the information being based upon spatio-spectral aspects of the image and constituents of color depicted in the image, in a matrix equation expressed by;

[A] [x]=[b], wherein [A] expresses values determined by a constraining relationship imposed upon the information relevant to a logical deduction regarding material and illumination aspects of the image, [b] expresses information obtained from the image file, in the computer memory, and [x] expresses an unknown material/illumination component of the image; and

utilize the matrix equation in an image segregation operation.

17. The computer program product of claim 16 wherein the spatio-spectral aspects of the image comprises spatio-spectral operators.

18. The compute program product of claim 16 wherein the constraining relationship is arranged to preserve shading contributing to an appearance of curvature of features depicted in the image, and to reduce shadowing effects.

19. The computer program product of claim 18 wherein the constraining relationship comprises a constraint based upon a tone mapping of the image.

20. The computer program product of claim 19 wherein the constraint based upon a tone mapping of the image is expressed by log t_R +log t_G +log t_B =V, where t_R is an average for a red channel of material for pixels of a token t, t_G is an average for a green channel of material for pixels of the token t, t_B is an average for material for a blue channel of pixels of the token t, and where V is an average for a calculated intensity value for the token t, derived from the tone mapping.

21. The computer program product of claim 20 wherein the constraint includes a second constraint based upon a chromaticity aspect of color depicted in the image.