Means for using microstructure of materials surface as a unique identifier
The present application concerns the visual identification of materials or documents for tracking or authentication purposes. It describes methods to automatically authenticate an object by comparing some object images with reference images, the object images being characterized by the fact that visual elements used for comparison are non-disturbing for the naked eye. In some described approaches it provides the operator with visible features to locate the area to be imaged. It also proposes ways for real-time implementation enabling user friendly detection using mobile devices like smart phones.
1. A method of authenticating an article of manufacture, the surface of the article of manufacture featuring predetermined, reproducible macroscopic characteristics as well as random or pseudo-random, non-reproducible microstructure noise characteristics, the random or pseudo-random, non-reproducible microscopic noise characteristics rendering the article physically unique, the method comprising:
acquiring an image of the visible feature using a predetermined imaging technology to produce a visible feature image with an imaging lighting orientation and an imaging resolution sufficient to show a least one article surface microstructure feature at the pixel level;
generating an authentication pattern based on the visible feature image;
querying, with the imaging device, for a reference product item, a reference authentication pattern in a predetermined central server database;
receiving from the predetermined central server a reference authentication pattern;
comparing, with the imaging device, the authentication pattern with the received reference authentication pattern; and
authenticating, with the imaging device, the article of manufacture if the authentication pattern correlates with the reference authentication pattern within a predefined pattern matching threshold.
2. The method according to claim 1 , wherein the predetermined, reproducible macroscopic characteristics comprise the size, the shape or the colors of a graphic design.
3. The method according to claim 2 , wherein the graphic design size renders the graphic design discernible to a naked eye.
4. The method according to claim 2 , wherein the graphic design size renders the graphic design discernible only under magnification.
5. The method according to claim 2 , wherein the graphic design displays a serial number on the article surface.
6. The method according to claim 2 , wherein the graphic design displays a barcode on the article surface.
7. The method according to claim 2 , wherein the graphic design displays a datamatrix code on the article surface.
8. The method according to claim 1 , wherein the surface material of the article is metallic, and wherein the manufacturing technique comprises chemical or laser engraving, chemical etching, stamping, or brushing.
9. The method according to claim 8 , wherein the article is a luxury product with a metallic surface.
10. The method according to claim 9 , wherein the luxury product is a watch and the metallic surface is the back of the watch.
11. The method according to claim 1 , wherein the manufacturing technique is incapable of exactly reproducing the non-reproducible microstructure noise characteristics, whereby at least one article surface microstructure surface feature renders the article physically unique.
12. The method according to claim 1 , wherein the random or pseudo-random, non-reproducible microstructure noise characteristics comprise a predetermined resolution, coarseness, surface roughness, or other property enabling the imaging of at least one article surface microstructure feature at the pixel level using the predetermined imaging technology at a resolution below 4800 dpi.
13. The method according to claim 1 , wherein the authentication pattern is a filtered image of the visible image feature.