Granted Patent B2

US 10,235,597 · App. 15/180,252 · Granted Mar 19, 2019

Inventors: Matthias Voigt (Lawrenceville, NJ); Michael L. Soborski (Allentown, NJ); Rafik Ayoub (Princeton Junction, NJ)

Assignee: Sys-Tech Solutions, Inc.

G06K9/6215G06F17/30256G06F17/30277G06K7/10861G06K7/1413G06K7/1447G06K7/1452G06K9/18G06K9/4604G06K19/06028G06K19/06037

Abstract

Claims (74)

1. A method, on a computing device, for determining whether a mark is genuine, the method comprising:

receiving an image of a candidate mark;

using the received image, measuring a characteristic of a feature of the candidate mark, resulting in a set of measurements;

creating a profile for the feature based on the set of measurements;

creating a first filtered profile for the feature by filtering, from the profile of the feature, all spatial frequency components except for those in a first spatial frequency band;

creating a second filtered profile for the feature by filtering, from the profile of the feature, all spatial frequency components except for those in a second spatial frequency band;

comparing the first filtered profile of the feature with an equivalent first filtered profile of a feature of a genuine mark;

comparing the second filtered profile of the feature with an equivalent second filtered profile of a feature of the genuine mark;

determining whether the candidate mark is genuine based on the first filtered profile comparison and the second filtered profile comparison; and

indicating a result of the determination to a user,

wherein the first spatial frequency band contains a first range of spatial frequencies and the second spatial frequency band contains a second range of spatial frequencies, and

wherein the second range is different from the first range.

2. The method of claim 1 , further comprising:

receiving an image of the genuine mark;

using the received image of the genuine mark, measuring a characteristic of a feature of the genuine mark, resulting in a set of measurements;

creating a profile for the feature of the genuine mark based on the set of measurements of the feature of the genuine mark;

creating the equivalent first filtered profile of the genuine mark by filtering, from the profile of the feature of the genuine mark, all spatial frequency components except for those in the first spatial frequency band; and

creating the equivalent second filtered profile of the genuine mark by filtering, from the profile of the feature of the genuine mark, all spatial frequency components except for those in the second spatial frequency band.

3. The method of claim 1 , wherein

the feature is an edge of the mark,

measuring the characteristic of the feature of the candidate mark comprises calculating a plurality of projected average pixel values in a portion of the mark that includes the edge, and

creating the profile for the feature comprises creating a profile of the edge based the calculated plurality of projected average pixel values calculated in a portion of the candidate mark that includes the edge.

4. The method of claim 3 , wherein calculating the plurality of projected average pixel values comprises calculating at least one projected pixel value along a line that runs from a first reference axis that extends in a direction generally parallel to the edge to a second reference axis that extends in a direction generally parallel to the edge.

5. The method of claim 4 , wherein the mark is a barcode, the first reference axis is within a bar of the barcode, and the second reference axis is between bars of the barcode.

6. The method of claim 4 , wherein the mark is a barcode, the first reference axis is within a bar of the barcode, and the second reference axis is within the bar.

7. The method of claim 4 , wherein the mark is a barcode, the first reference axis is between bars of the barcode, and the second reference axis is between bars of the barcode.

8. The method of claim 1 , further comprising:

creating further filtered profiles for the feature for further spatial frequency bands; and

comparing each of the further filtered profiles with equivalent filtered profiles of the feature on the genuine mark,

wherein determining whether the candidate mark is genuine is further based on the further filtered profiles.

9. The method of claim 1 , further comprising:

assigning a first correlation score to the first spatial frequency band based on the comparison of the first filtered profile of the feature with the equivalent first filtered profile of the feature of the genuine mark;

assigning a second correlation score to the second spatial frequency band based on the comparison of the second filtered profile of the feature with the equivalent second filtered profile of the feature of the genuine mark; and

creating a spatial frequency spectrum correlation profile using the first correlation score and the second correlation score,

wherein determining whether the candidate mark is genuine comprises determining whether the candidate mark is genuine based on at least one of the first and second correlation scores.

10. The method of 9 , wherein

creating the spatial frequency spectrum correlation profile comprises:

mapping the first correlation score to a first band-pass filter of the first spatial frequency band; and

mapping the second correlation score to a second band-pass filter of the second spatial frequency band, and

determining whether the candidate mark is genuine comprises analyzing the mapped correlation scores and spatial frequency bands.

11. The method of claim 1 , wherein

creating the first filtered profile comprises applying a first band-pass filter to the feature profile;

creating the second filtered profile comprises a second band-pass filter to the feature profile separately from the application of the first band-pass filter.

12. The method of claim 1 , wherein the feature is an artifact.

13. The method of claim 1 , wherein the feature is a subarea of the candidate mark, and the measurement is a measurement of the average pigmentation of the subarea.

14. The method of claim 1 , wherein the feature is a subarea of the candidate mark, and the measurement is a measurement of deviation in the position of the subarea from a best-fit grid.

15. The method of claim 1 , wherein the feature is a subarea of the candidate mark, and the measurement is a measurement of stray marks or voids in the subarea.

16. The method of claim 1 , wherein receiving the image of the candidate mark comprises receive the image from a camera built into the computing device.

17. The method of claim 1 , wherein receiving the image of the candidate mark comprises receive via a network.

18. The method of claim 1 , wherein the mark is selected from a group consisting of a barcode, a logo, and a decoration.

19. A computing device comprising a hardware processor that carries out actions comprising:

receiving an image of a candidate mark;

using the received image, making a plurality of measurements of a feature of the candidate mark;

creating a profile for the feature based on the plurality of measurements;

creating a first filtered profile for the feature by filtering, from the profile of the feature, all spatial frequency components except for those in a first spatial frequency band;

creating a second filtered profile for the feature by filtering, from the profile of the feature, all spatial frequency components except for those in a second spatial frequency band;

comparing the first filtered profile of the feature with an equivalent first filtered profile of a feature of a genuine mark;

comparing the second filtered profile of the edge with an equivalent second filtered profile of a feature of the genuine mark;

determining whether the candidate mark is genuine based on the first filtered profile comparison and the second filtered profile comparison; and

indicating a result of the determination to a user,

wherein the first spatial frequency band contains a first range of spatial frequencies and the second spatial frequency band contains a second range of spatial frequencies, and

wherein the second range is different from the first range.

20. A non-transitory computer-readable medium having stored thereon computer-executable instructions for carrying out actions comprising:

receiving an image of a candidate mark;

using the received image, making a plurality of measurements of a feature of the candidate mark;

creating a profile for the feature based on the plurality of measurements;

creating a first filtered profile for the feature by filtering, from the profile of the feature, all spatial frequency components except for those in a first spatial frequency band;

creating a second filtered profile for the feature by filtering, from the profile of the feature, all spatial frequency components except for those in a second spatial frequency band;

comparing the first filtered profile of the feature with an equivalent first filtered profile of a feature of a genuine mark;

comparing the second filtered profile of the edge with an equivalent second filtered profile of a feature of the genuine mark;

determining whether the candidate mark is genuine based on the first filtered profile comparison and the second filtered profile comparison; and

indicating a result of the determination to a user,

wherein the first spatial frequency band contains a first range of spatial frequencies and the second spatial frequency band contains a second range of spatial frequencies, and

wherein the second range is different from the first range.

Assignments (4)

Continuity (2)

Cited By (10)

US 12,194,886 US 12,224,611 US 12,227,108 US 12,296,717 US 12,296,721 US 12,441,212 US 12,462,345 US 12,533,968 US 12,539,773 US 12,614,046