Texture identification

1. A method for determining a texture of an object, the method comprising:

receiving a two-dimensional image representative of a surface of the object;

estimating a three-dimensional (3D) projection of the image;

transforming the 3D projection into a frequency domain;

projecting the 3D projection in the frequency domain onto a spherical co-ordinate system;

determining the texture of the surface by generating and analyzing spectral signatures for a tilt angle variation and an orientation angle variation extracted from the 3D projection on the spherical co-ordinate system;

calculating a tilt angle value based on a comparison of sum of peak to peak distance between the spectral signature for the tilt angle variation and a reference spectral signature for the tilt angle variation;

calculating an orientation angle value based on a comparison of sum of peak to peak distance between the spectral signature for the orientation angle variation and a reference orientation angle variation; and

generating a texture value based on the tilt angle value and the orientation angle value.

2. The method of claim 1 , wherein the transforming the 3D projection comprises using a 3D Fourier transform.

3. The method of claim 1 , wherein the estimating the 3D projection comprises projecting the two dimensional image on to a Cartesian coordinate system.

4. The method of claim 1 , further comprising classifying the surface into at least one texture type from among a plurality of texture types.

5. The method of claim 4 , further comprising classifying the surface into the at least one texture type based on a plurality of parameters comprising at least one of homogeneity, directionality, regularity, or roughness.

6. The method of claim 1 , wherein the texture value is the sum of the tilt angle value and the orientation angle value.

7. The method of claim 1 , further comprising selecting a comparison that generates a minimum texture value.

8. A non-transitory computer program product, for use in a computing system including a processor and a memory, for implementing a method for performing texture identification of an object, the non-transitory computer program product comprising one or more physical computer readable medium having stored thereon computer-executable instructions that, when executed by the processor, causes the computing system to:

access a two-dimensional image representative of a surface of the object;

estimate a three-dimensional (3D) projection of the image;

transform the 3D projection into a frequency domain;

project the 3D projection in the frequency domain on to a spherical co-ordinate system;

determine the texture of the surface by generating and analyzing spectral signatures for a tilt angle variation and an orientation angle variation extracted from the 3D projection on the spherical co-ordinate system;

calculate a tilt angle value based on a comparison of sum of peak to peak distance between the spectral signature for the tilt angle variation and a reference spectral signature for tilt angle variation;

calculate an orientation angle value based on a comparison of a sum of peak to peak distance between the spectral signature for the orientation angle variation and a reference orientation angle variation; and

generate a texture value based on the tilt angle value and the orientation angle value.

9. The non-transitory computer program product of claim 8 , wherein the estimation of the 3D projection is by projecting the two dimensional image on to a Cartesian coordinate system.

10. The non-transitory computer program product of claim 8 , wherein the computer-executable instructions, when executed by the processor, further cause the computing system to classify the surface into at least one texture type from among a plurality of texture types.

11. The non-transitory computer program product of claim 10 , wherein the computer-executable instructions, when executed by the processor, cause the computing system to classify the surface into the at least one texture type based on a plurality of parameters comprising at least one of homogeneity, directionality, regularity, or roughness.

12. The non-transitory computer program product of claim 8 , wherein the computer-executable instructions, when executed by the processor, further cause the computing system to select a comparison that generates a minimum texture value.

13. The non-transitory computer program product of claim 8 , wherein the texture value is the sum of the tilt angle value and the orientation angle value.

14. A system to determine a texture of an object, the system comprising:

a memory configured to store a two-dimensional image representative of a surface of the object; and

a processor configured to:

access the two-dimensional image,

estimate a three-dimensional (3D) projection of the image,

transform the 3D projection into a frequency domain,

project the 3D projection in the frequency domain on to a spherical co-ordinate system,

determine the texture of the surface by generating and analyzing spectral signatures for a tilt angle variation and an orientation angle variation extracted from the 3D projection on the spherical co-ordinate system,

calculate a tilt angle value based on a comparison of sum of peak to peak distance between the spectral signature for the tilt angle variation and a reference spectral signature for the tilt angle variation,

calculate an orientation angle value based on a comparison of sum of peak to peak distance between the spectral signature for the orientation angle variation and a reference orientation angle variation, and

generate a texture value based on the tilt angle value and the orientation angle value.

15. The system of claim 14 , wherein the processor is configured to transform the 3D projection into the frequency domain using a 3D Fourier transform.

16. The system of claim 14 , wherein the processor configured to estimate the 3D projection of the image comprises the processor configured to project the two dimensional image on to a Cartesian coordinate system.

17. The system of claim 14 , wherein the processor is further configured to classify the surface into at least one texture type from among a plurality of texture types.

18. The system of claim 17 , wherein the processor is configured to classify the surface into the at least one texture type based on a plurality of parameters comprising at least one of homogeneity, directionality, regularity, or roughness.

19. The system of claim 14 , wherein the texture value is the sum of the tilt angle value and the orientation angle value.

20. The system of claim 14 , wherein the processor is further configured to select a comparison that generates a minimum texture value.