Preserving authentication under item change

• US 10,346,852 B2
• Filed: 02/17/2017
• Issued: 07/09/2019
• Est. Priority Date: 02/19/2016
• Status: Active Grant

• Current Assignee: Alitheon, Inc.
• Original Assignee: Alitheon, Inc.
• Inventors: Ross, David Justin, Withrow, Justin Lynn, Land, Scot E., Kim, David Keesu, Tocci, Mark, Ross, Robert Saxon
• Primary Examiner(s): Li, Ruiping
• Application Number:
  US15/436,616
• Publication Number:
  US 20170243230A1
• Time in Patent Office: 872 Days
• CPC Class Codes: G06F 16/51 Indexing; Data structures therefor; Storage structures
• CPC Class Codes: G06F 16/5838 using colour
• CPC Class Codes: G06F 16/5866 using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
• CPC Class Codes: G06F 16/587 using geographical or spatial information, e.g. location
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06F 21/44 Program or device authentication
• CPC Class Codes: G06F 21/73 by creating or determining hardware identification, e.g. serial numbers
• CPC Class Codes: G06F 2221/2111 Location-sensitive, e.g. geographical location, GPS
• CPC Class Codes: G06Q 30/0185 Product, service or business identity fraud
• CPC Class Codes: G06V 10/44 Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
• CPC Class Codes: G06V 10/462 Salient features, e.g. scale invariant feature transforms [SIFT]
• CPC Class Codes: G06V 10/50 by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
• CPC Class Codes: G06V 10/751 Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
• CPC Class Codes: G06V 20/80 Recognising image objects characterised by unique random patterns
• CPC Class Codes: G06V 20/95 Pattern authentication; Markers therefor; Forgery detection
• CPC Class Codes: H04L 9/3278 using physically unclonable functions [PUF]

Abstract

Apparatuses and methods associated with preserving authentication under item change are disclosed herein. In embodiments, acquiring digital image data of an image of at least a portion of a target physical object; extracting features from the image data to form a digital fingerprint; querying the database system to seek a matching record based on the digital fingerprint; based on an amount of difference between the digital fingerprint and a stored digital fingerprint of the database, update the database system to output a new indication of a new match to the physical object for any new samples that are not matchable to the stored digital fingerprint within a first predetermined similarity threshold provided the new samples are matchable to the digital fingerprint within a second predetermined similarity threshold. Other embodiments may be disclosed or claimed.

Claims

1. A method, comprising:

providing a database system having a processor;

storing in the database system a first digital fingerprint based on first digital image data of a first digital image of at least a portion of a physical object, wherein the first digital fingerprint is responsive to a natural structure of the physical object and includes at least a first feature vector, wherein the first feature vector includes a series of numbers responsive to a region of interest of the first digital image data;

acquiring second digital image data of a second digital image of at least a portion of a target physical object wherein the second digital image was captured at a second time subsequent to a first time when the first digital image was captured;

extracting, via a processor, features from the second digital image data, said features associated with a region of interest of the second digital image data;

forming, via the processor, a second digital fingerprint that is responsive to a natural structure of the target physical object and includes at least a second feature vector, wherein the second feature vector includes a series of numbers responsive to the extracted features;

querying the database system processor to seek a matching record based on the second digital fingerprint;

in the database system processor, responsive to the querying, determining an amount of difference between the first and second digital fingerprints, the determination of the amount of difference including comparing the first and second feature vectors;

in the database system processor, in a first case that the amount of difference between the first and second digital fingerprints is within a first predetermined similarity threshold, returning an indication of a match to the first digital fingerprint; and

in the database system processor, in a second case that the amount of difference between the first and second digital fingerprints exceeds the first predetermined similarity threshold and is within a second predetermined similarity threshold, generating an indication of a new match to the physical object, and storing the second digital fingerprint in the database system associated with the first digital fingerprint as an additional identifier of the physical object, and including in the database system an indication of the second time that the second digital image data was captured.

2. The method of claim 1, further comprising:

in a third case that the amount of difference between the first and second digital fingerprints exceeds both the first predetermined similarity threshold and the second predetermined similarity threshold, returning an indication of non-match.

3. The method of claim 2, further comprising:

acquiring a third digital fingerprint;

in the database system processor, comparing the third digital fingerprint to the first and second digital fingerprints;

based on the comparing steps, selecting one of the first and second digital fingerprints as a best match to the third digital fingerprint; and

in a case that the best match has an amount of difference that is between the first predetermined similarity threshold and the second predetermined similarity threshold, adding the third digital fingerprint to the database system as an additional identifier of the physical object.

4. The method of claim 3, wherein the first, second and third digital fingerprints each include respective feature vectors and comparing the third digital fingerprint to at least one of the first and second digital fingerprints includes comparing the respective feature vectors as one metric of similarity or closeness of match.

5. The method of claim 3, wherein comparing the third digital fingerprint to at least one of the first or second digital fingerprints includes comparing the third digital fingerprint to selected digital fingerprints of all digital fingerprints of the database system.

6. The method of claim 1, further comprising:

adding the second digital fingerprint to a database record for the physical object responsive to matching the second digital fingerprint to the first digital fingerprint, so that the database record stores a sequence of digital fingerprints, wherein a most recent digital fingerprint of the stored sequence of digital fingerprints includes the second digital fingerprint and a least recent digital fingerprint of the stored sequence of digital fingerprints includes the first digital fingerprint or a less recent digital fingerprint;

performing a selection from the stored sequence of digital fingerprints based on the amount of difference between the first and second digital fingerprints; and

retaining in the database system control information based on the selection, wherein said control information is to constrain one or more comparisons of another digital fingerprint of a next query to a subset of the digital fingerprints of the sequence of digital fingerprints or is to constrain a temporal order for performing a plurality of next comparisons of the another digital fingerprint to digital fingerprints of the sequence of digital fingerprints.

7. The method of claim 1, wherein the first and second feature vectors are multi-dimensional vectors and said comparing the first and second feature vectors includes calculating a distance between the first and second feature vectors.

8. The method of claim 1, further comprising:

identifying a third digital fingerprint, the third digital fingerprint similar to the second digital fingerprint within the second predetermined similarity threshold, the third digital fingerprint not similar to the first digital fingerprint within the first predetermined similarity threshold;

querying the database system to identify a sequence of digital fingerprints associated with the physical object, the sequence of digital fingerprints including at least the first, second, and third digital fingerprints;

based on the identified sequence of digital fingerprints, recognizing incremental changes to the natural structure of the physical object attributable to at least one of wear from use over time, addition of markings to the physical object over time, corrosion over time, or wear from transport based on incremental changes;

generating history data to characterize the incremental changes; and

causing the history data to be displayed on an electronic display.

9. The method of claim 8, further comprising:

identifying a sequence of metadata, wherein each metadata of the sequence of metadata is associated with a respective one of the digital fingerprints of the sequence of digital fingerprints;

correlating at least one of the incremental changes of wear from use over time, addition of markings to the physical object over time, corrosion over time, or wear from transport based on incremental changes based on the sequence of metadata; and

storing a result of the correlation in the database system.

10. The method of claim 9, wherein the metadata of the sequence of metadata specifies locations of scans to generate the digital fingerprints of the sequence of digital fingerprints.

11. The method of claim 9, further comprising:

correlating the at least one of the incremental changes to the natural structure to transport along a supply chain based on location data of the sequence of metadata; and

displaying information about the correlating.

12. The method of claim 9, further comprising:

correlating the at least one of the incremental changes to a time period based on time data of the sequence of metadata;

wherein the correlation to at least one of wear from use over time, addition of markings to the physical object over time, corrosion over time, or wear from transport based on incremental changes is based on the correlation to the time period.

13. The method of claim 8, wherein the corrosion over time comprises oxidative damage.

14. The method of claim 8, wherein the wear from use over time comprises abrasion of a security region of the physical object.

15. The method of claim 14, wherein the physical object comprises a credit card.

16. The method of claim 8, wherein said recognizing incremental changes includes detecting the addition of material to the physical object to mark the physical object based on comparing different digital fingerprints of the sequence of digital fingerprints.

17. The method of claim 8, wherein said recognizing incremental changes includes detecting the removal of material from the physical object to mark the physical object based on comparing different digital fingerprints of the sequence of digital fingerprints.

18. The method of claim 1, further comprising:

storing the second digital fingerprint in the database record.

19. The method of claim 18, further comprising:

retaining the first digital fingerprint responsive to updating the database system to provide a stored sequence of digital fingerprints associated with the physical object.

20. The method of claim 1, further comprising:

updating a database record of the database system based on a result of determining the amount of difference by replacing the first digital fingerprint with the second digital fingerprint in the database record.

21. The method of claim 1, wherein the region of interest of the first digital image data is a specific feature in the first digital image and the region of interest of the second digital image date is a specific feature in the second digital image.