Model-based digital fingerprinting

1. A digital fingerprinting method, comprising:

acquiring first image data of a portion of a surface of a first physical object;

constructing a first model of the portion of the surface of the first physical object from the first image data, wherein the first model includes a plurality of surface features of the portion of the surface of the first physical object;

extracting a selection of surface features from the plurality of surface features included in the first model based on one or more authentication regions specified for a class of physical objects to which the first physical object belongs, each of the one or more authentication regions corresponding to a respective sub-region;

determining a first digital fingerprint based on the selection of surface features, wherein the first digital fingerprint uniquely identifies the first physical object from other physical objects in the class of physical objects to which the first physical object belongs; and

inducting the first physical object into a reference database system by storing a record in the reference database system that includes the first digital fingerprint of the first model that uniquely identifies the first physical object from other physical objects in the class of physical objects to which the first physical object belongs.

2. The method of claim 1 , wherein the first model is based on native properties of the first physical object without recognizing identifying content attached to the first physical object.

3. The method of claim 1 , further comprising:

scanning a second physical object to capture second image data of a portion of a surface of the second physical object;

constructing a second model of the portion of the surface of the second physical object from the second image data, the second model based on native properties of the second physical object, without recognizing identifying content attached to the second physical object;

extracting a second digital fingerprint based on the second model based on one or more authentication regions specified for the class of physical objects to which the first and the second physical objects belong;

comparing the second digital fingerprint to the characterizing first digital fingerprint to attempt to authenticate the second physical object as being the first physical object; and

generating a report based on the comparing.

4. The method of claim 1 , further comprising:

scanning a second physical object to capture second image data of the second physical object;

extracting a third digital fingerprint from the second image data based on one or more authentication regions specified for the class of physical objects to which the first and the second physical objects belong, the third digital fingerprint based on native properties of the second physical object without recognizing identifying content attached to the second physical object;

comparing the third digital fingerprint to the first digital fingerprint to obtain a result; and

generating a report based on the comparing.

5. The method of claim 1 , further comprising:

querying a reference database system based on at least one digital fingerprint.

6. The method of claim 1 , further comprising:

acquiring additional image data from a plurality of images of the portion of the first physical object; and

constructing the first model of the first physical object based on the first image data and the additional image data.

7. The method of claim 1 wherein the first model is substantially invariant to changes in at least one selected condition from among a set of conditions that includes: Scale, Rotation, Affine, Homography, Perspective, and Illumination.

8. The method of claim 1 , wherein constructing a first model of the portion of the surface of the first physical object from the first image data comprises:

creating a three-dimensional map of the portion of the surface of the first physical object; and

converting the three-dimensional map into a digital representation of the portion of the surface.

9. The method of claim 1 , further comprising:

detecting a plurality of points of interest on the portion of the surface of the first physical object represented in the first model;

characterizing each point of interest by a respective feature vector; and

augmenting each feature vector with at least one of three-dimensional coordinates of the respective point of interest on the portion of the surface, a surface shape characteristic, chroma, and reflectance.

10. The method of claim 1 , further comprising:

identifying a plurality of points of interest on the portion of the surface of the first physical object; and

producing an n-dimensional model of the first physical object, wherein each of the identified plurality of points of interest is characterized by an n-dimensional vector.

11. The method of claim 10 wherein producing an n-dimensional model of the first physical object comprises producing the n-dimensional vector associated with a plurality of parameters including at least one of: an (x, y, z) location of the corresponding identified point of interest on the portion of the surface of the first physical object, a surface shape characteristic, chroma, and reflectance.

12. The method of claim 1 , wherein determining a first digital fingerprint based on the selection of surface features comprises:

generating a digital fingerprint of the first physical object based on the digital representation, without reference to any image of the first physical object.

13. The method of claim 1 , wherein inducting the first physical object into a reference database system comprises:

storing the digital fingerprint for at least one of subsequent authentication, tracking, and identification.

14. The method of claim 1 , wherein extracting a selection of surface features from the plurality of surface features included in the first model based on one or more authentication regions specified for a class of physical objects to which the first physical object belongs, comprises extracting the selection of surface features for one respective sub-region.

15. The method of claim 1 , wherein extracting a selection of surface features from the plurality of surface features included in the first model based on one or more authentication regions specified for a class of physical objects to which the first physical object belongs, comprises extracting the selection of surface features for two or more respective sub-regions.

16. The method of claim 1 , wherein extracting a selection of surface features from the plurality of surface features included in the first model based on one or more authentication regions specified for a class of physical objects to which the first physical object belongs, comprises extracting the selection of surface features for two or more respective sub-regions but less than all sub-regions.