Database for detecting counterfeit items using digital fingerprint records
Improvements are disclosed for detecting counterfeit objects, based on comparison to digital fingerprints that describe features found in images of objects known to be counterfeit.
1. A machine comprising:
an input device that captures image data of at least a portion of a suspect physical object; and
a digital fingerprint system having a processor and a memory wherein the processor is configured to
create a digital fingerprint of the suspect physical object based on the image data, wherein the digital fingerprint includes a first piece of data identifying a plurality of regions of interest of the suspect physical object and, for each region of interest, a second piece of data forming at least one fingerprint feature vector that describes a fingerprint feature extracted from the region of interest of the suspect physical object;
store the created digital fingerprint for the suspect physical object in a database, the database having stored therein multiple digital fingerprints associated with multiple physical objects, wherein the digital fingerprint identifies the suspect physical object as being unique among the multiple physical objects.
2. The machine of claim 1 , wherein the input device includes at least one optical sensor.
3. The machine of claim 1 , wherein the fingerprint feature includes manufacturing features of the suspect physical object.
4. The machine of claim 1 , wherein the processor of the digital fingerprint system is further configured to extract a unique identifier from the suspect physical object; and
store the unique identifier in the database to augment search and identification of the suspect physical object.
5. The machine of claim 1 , wherein the input device further captures image data of at least a portion of a reference physical object that is manufactured according to a specification of a manufacturer; and
the processor of the digital fingerprint system is further configured to create a digital fingerprint of the reference physical object, wherein the digital fingerprint of the reference physical object includes a first piece of data identifying a plurality of regions of interest of the reference physical object and, for each region of interest, a second piece of data forming at least one reference feature vector that describes a fingerprint feature extracted from the region of interest of the reference physical object, wherein the digital fingerprint of the reference physical object serves as a proxy for the specification of the manufacturer; and
store the digital fingerprint of the reference physical object in the database.
6. The machine of claim 5 , wherein processor of the digital fingerprint system is further configured to compare the digital fingerprint of the suspect physical object to the digital fingerprint of the reference physical object to generate a result that determines whether the suspect physical object was manufactured in conformance with the specification of the manufacturer;
determine the result indicates a match between the at least one fingerprint feature vector included in the digital fingerprint of suspect physical object and the at least one reference feature vector included in the digital fingerprint of the reference physical object; and
determine the suspect physical object is manufactured in conformance with the specification of the manufacturer based on the match.
7. The machine of claim 1 , wherein the fingerprint feature of the suspect physical object includes dimensional qualities associated with at least one physical feature of the suspect physical object.
8. The machine of claim 1 , wherein the fingerprint feature of the suspect physical object includes non-alpha-numeric, optically discernible features of the suspect physical object.
9. The machine of claim 1 , wherein the fingerprint feature of the suspect physical object includes multiple known indicia of a counterfeit or forged object.
10. The machine of claim 1 , wherein the processor of the digital fingerprint system is further configured to parse the image data into the plurality of regions of interest;
collect a piece of region-of-interest data from each region of interest of the image data;
generate identifier data for each region of interest, the identifier data pairing an identifier with the region-of-interest data of a corresponding region of interest;
and
associate the identifier data with the digital fingerprint of the suspect physical object.
11. The machine of claim 10 , wherein the database includes at least one list of classification elements and individual element values for each of the classification elements, wherein each classification element and its corresponding individual element values together define a corresponding pattern, and wherein the database is arranged to support searching a plurality of patterns for a match based on identifier data associated with digital fingerprints stored in the database.
12. The machine of claim 1 , wherein the digital fingerprint of the suspect physical object is based on image data of the portion of the suspect physical object, wherein the image data is independent from identifying information about the suspect physical object included in tags, labels, or other materials added to the suspect physical object.
13. The machine of claim 1 , wherein the processor of the digital fingerprint system is further configured to
extract information from the image data;
categorize the extracted information to determine a category; and
include a category indicator in the digital fingerprint of the suspect physical object.
14. The machine of claim 1 , wherein the pieces of data of the digital fingerprint of the suspect physical object are responsive to one or more characteristics appearing in a presentable image generated from the image data, the one or more characteristics including a plurality of markings discernible in the presentable image together with respective region data of each of the plurality of markings.
15. The machine of claim 14 , wherein the pieces of data of the digital fingerprint of the suspect physical object include size data for each of the plurality of markings.
16. The machine of claim 14 , wherein the pieces of data of the digital fingerprint of the suspect physical object include dimension data for each of the plurality of markings, the dimension data defined, at least in part, by corresponding dimensions of each respective marking.
17. The machine of claim 14 , wherein the pieces of data of the digital fingerprint of the suspect physical object include pixel-count data for each of the plurality of markings, the pixel-count data defined, at least in part, by a total pixel count of each respective marking.
18. A system comprising:
a processor and memory connected to each other;
a database connected to the processor, wherein the database stores multiple digital fingerprints associated with multiple physical objects;
an input device connected to the processor;
a network interface configured to communicate with the processor and the input device over a network; and
a plurality of lines of instructions stored in the memory and executed by the processor of the system that is configured to
acquire, from the input device, image data of at least a portion of a suspect physical object;
create a digital fingerprint of the suspect physical object based on the image data, wherein the digital fingerprint includes a first piece of data identifying a plurality of regions of interest of the suspect physical object and, for each region of interest, a second piece of data forming at least one fingerprint feature vector that describes a fingerprint feature extracted from the region of interest; and
store the digital fingerprint in the database, wherein the digital fingerprint identifies the suspect physical object as being unique among the multiple physical objects.
19. The system of claim 18 , wherein the fingerprint feature includes manufacturing features of the suspect physical object.
20. The system of claim 18 , wherein the processor is further configured to acquire, from the input device, image data of at least a portion of a reference physical object that is manufactured according to a specification of a manufacturer;
create a digital fingerprint of the reference object, wherein the digital fingerprint of the reference physical object includes a first piece of data identifying a plurality of regions of interest of the reference physical object and, for each region of interest, a second piece of data forming at least one reference feature vector that describes a fingerprint feature extracted from the region of interest of the reference physical object; and
store the digital fingerprint of the reference physical object in the database.
21. The system of claim 20 , wherein the processor is further configured to compare the digital fingerprint of the suspect physical object to the digital fingerprint of the reference physical object to generate a result that determines whether the suspect physical object was manufactured in conformance with the specification of the manufacturer;
determine the result indicates a match between the at least one fingerprint feature vector included in the digital fingerprint of the suspect physical object and the at least one reference feature vector included in the digital fingerprint of the reference physical object; and
determine the suspect physical object is manufactured in conformance with the specification of the manufacturer based on the match.