Product, image, or document authentication, verification, and item identification

• US 9,053,364 B2
• Filed: 10/30/2013
• Issued: 06/09/2015
• Est. Priority Date: 10/30/2012
• Status: Active Grant

• Current Assignee: Authentiform LLC
• Original Assignee: Authentiform LLC
• Inventors: Mercolino, Thomas J., Freeman, Darrell Jerome Jr., Stephenson, Robert Brooks, Tapadia, Hersh Ashok
• Primary Examiner(s): SHAH, UTPAL D
• Application Number:
  US14/067,945
• Publication Number:
  US 20140119615A1
• Time in Patent Office: 587 Days
• Field of Search: 382/112, 382/218, 382/219
• US Class Current: 1/1
• CPC Class Codes: B42D 25/305 Associated digital information record carriers for use with machines and with at least a part designed to carry digital markings G06K19/00
• CPC Class Codes: G06F 2218/12 Classification; Matching
• CPC Class Codes: G06K 19/06037 multi-dimensional coding
• CPC Class Codes: G06K 19/10 at least one kind of marking being used for authentication, e.g. of credit or identity cards verification of coded identity or credit cards in mechanisms actuated by them G07F7/12
• CPC Class Codes: G06K 7/00 Methods or arrangements for sensing record carriers, e.g. for reading patterns methods or arrangements for marking the record carrier in digital fashion G06K1/00; pattern recognition G06F18/00; arrangements for image or video recognition or understanding G06V10/00; character recognition, recognising digital ink or document-oriented image-based pattern recognition G06V30/00
• CPC Class Codes: G06K 7/10 by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
• CPC Class Codes: G06V 40/30 Writer recognition; Reading and verifying signatures
• CPC Class Codes: G07D 7/004 using digital security elements, e.g. information coded on a magnetic thread or strip
• CPC Class Codes: G07D 7/2033 Matching unique patterns, i.e. patterns that are unique to each individual paper
• CPC Class Codes: G07D 7/206 Matching template patterns

Abstract

The present disclosure provides methods, reagents, and apparatus for authenticating and identifying products. Methods of the disclosure are easy to implement but difficult to replicate, simulate, alter, transpose, or tamper with. In some embodiments, the present disclosure relates to a method of authenticating products using a product authentication code defined by a frequency array of a population of entities, and an item identifier defined by the specific manifestation of the product authentication code.

Claims

1. A method of determining differences between items of interest, the method comprising:

receiving an item of interest, wherein the item of interest is associated with a signature;

comparing the item of interest to a set of reference images that comprises a series of reference shapes including at least two distinct, spatially-separated reference shapes in a same plane;

determining a plurality of similarity scores between the item of interest and the set of reference images by comparing the reference images and the item of interest;

determining an error vector based on the plurality of similarity scores; and

comparing the determined error vector with an error vector created from an authentic item associated with the signature.

2. A method of calculating the similarity between two or more images, the method comprising:

selecting a set of reference images that comprises a series of reference shapes including at least two distinct, spatially-separated reference shapes in a same plane;

selecting a target image that comprises a series of target shapes including at least two distinct, spatially-separated target shapes in a same plane;

scaling the target image substantially to the set of reference images;

comparing the target image to the set of reference images by comparing the target shapes with the reference shapes;

determining a plurality of similarity scores between the set of reference images and the target image by comparing the reference image and the target image; and

determining an error vector based on the plurality of similarity scores.

3. The method of claim 2, wherein the set of reference images are a set of shapes.

4. The method of claim 3, wherein the shapes in the set of shapes are approximately equivalent.

5. The method of claim 3, wherein the shapes are separable relative to one another.

6. The method of claim 3, wherein at least eight different shapes form the set of shapes.

7. The method of claim 3, wherein the shapes are aligned or closely aligned to a particular axis.

8. The method of claim 2, wherein each of the set of reference images and set of target images are compared based on a percentage of the reference image that is occupied by the reference shapes and a percentage of the target image that is occupied by the target shapes.

9. The method of claim 2, wherein the same plane is a flat plane.