Counterfeit detection scheme using paper surfaces and mobile cameras

1. A method, comprising:

illuminating a surface of an item with a lighting source of a device;

capturing a plurality of images of the surface by a camera of the device during the illumination of the surface;

authenticating the item based on the plurality of images;

estimating a location of a lens of the camera; and

calculating a direction of incident light for pixels of an area of the surface based on the estimation,

wherein the authentication is based on a microscopic normal vector field of the surface determined based on the direction of incident light.

2. The method of claim 1 , further comprising:

estimating a microscopic normal vector field of the surface, wherein the authentication is based on the estimate of the microscopic normal vector field.

3. The method of claim 1 , wherein the authentication is based on physical characteristics of the surface.

4. The method of claim 3 , wherein the authentication is based on physically unclonable properties of the surface.

5. The method of claim 1 , wherein the authentication is based on comparing the appearance of the plurality of images to reference images.

6. The method of claim 1 , wherein the authentication comprises detecting that the item is a duplicate or counterfeit.

7. The method of claim 1 , further comprising:

weighting non-uniform intensity according to different estimated distances from pixel locations to the lighting source when calculating the direction of incident light.

8. The method of claim 1 , further comprising:

providing an authentication output to a user of the device.

9. An apparatus, comprising:

a light of a device configured to illuminate a surface of an item;

a camera of the device configured to capture a plurality of images of the surface during the illumination of the surface;

a processor of the device configured to authenticate the item based on the plurality of images,

estimate a location of a lens of the camera; and

calculate a direction of incident light for pixels of an area of the surface based on the estimation,

wherein the authentication is based on the direction of incident light.

10. The apparatus of claim 9 , wherein the processor is further configured to estimate a microscopic normal vector field of the surface, wherein the authentication is based on the estimate of the microscopic normal vector field.

11. The apparatus of claim 9 , wherein the authentication is based on physical characteristics of the surface.

12. The apparatus of claim 11 , wherein the authentication is based on physically unclonable properties of the surface.

13. The apparatus of claim 9 , wherein the authentication comprises detecting that the item is a duplicate or counterfeit.

14. The apparatus of claim 9 , wherein the device comprises a mobile device.

15. The method of claim 9 , wherein the authentication is based on comparing the appearance of the plurality of images to reference images.

16. The apparatus of claim 9 , wherein the processor is further configured to weight non-uniform intensity according to different estimated distances from pixel locations to the lighting source when authenticating the item.

17. The apparatus of claim 9 , further comprising:

a user interface configured to provide an authentication output to a user of the device.

18. An apparatus, comprising:

means for illuminating a surface of an item with a lighting source of a device;

means for capturing a plurality of images of the surface by a camera of the device during the illumination of the surface;

means for authenticating the item based on the plurality of images;

means for estimating a location of a lens of the camera; and

means for calculating a direction of incident light for pixels of an area of the surface based on the estimation,

wherein the authentication is based on the direction of incident light.

19. The apparatus of claim 18 , further comprising:

means for estimating a microscopic normal vector field of the surface, wherein the authentication is based on the estimate of the microscopic normal vector field.

20. The apparatus of claim 18 , wherein the authentication is based on physical characteristics of the surface.

21. The apparatus of claim 20 , wherein the authentication is based on physically unclonable properties of the surface.

22. The apparatus of claim 18 , wherein the authentication is based on comparing the appearance of the plurality of images to reference images.

23. The apparatus of claim 18 , wherein the authentication comprises detecting that the item is a duplicate or counterfeit.

24. The apparatus of claim 18 , further comprising:

means for weighting non-uniform intensity according to different estimated distances from pixel locations to the lighting source when calculating the direction of incident light.

25. The apparatus of claim 18 , further comprising:

means for providing an authentication output to a user of the device.

26. A method, comprising:

illuminating a surface of an item with a lighting source;

capturing an image of the surface by a camera of a device during the illumination of the surface, wherein the capturing occurs with a predefined camera-surface geometry;

authenticating the item based on comparison of an appearance of the captured image to a reference appearance under the same predefined camera-surface geometry;

estimating a location of a lens of the camera; and

calculating a direction of incident light for every pixel of an area of the surface based on the estimation,

wherein the authentication is based on a microscopic normal vector field of the surface determined based on the direction of incident light.