Document fingerprinting

• US 9,350,552 B2
• Filed: 05/29/2014
• Issued: 05/24/2016
• Est. Priority Date: 03/02/2011
• Status: Active Grant

• Current Assignee: Alitheon, Inc.
• Original Assignee: Authentect, Inc.
• Inventors: Elmenhurst, Brian J., Ross, David Justin
• Primary Examiner(s): Cunningham, Gregory F
• Application Number:
  US14/290,653
• Publication Number:
  US 20140270341A1
• Time in Patent Office: 726 Days
• Field of Search: 382/101
• US Class Current: 1/1
• CPC Class Codes: B07C 5/3422 using video scanning devices, e.g. TV-cameras
• CPC Class Codes: G06F 16/2468 Fuzzy queries
• CPC Class Codes: G06F 16/583 using metadata automatically derived from the content
• CPC Class Codes: G06F 16/5846 using extracted text
• CPC Class Codes: G06Q 50/60 Business processes related to postal services shipping G06Q10/083; franking apparatus G07B17/00
• CPC Class Codes: G06T 7/60 Analysis of geometric attributes
• CPC Class Codes: G06T 7/90 Determination of colour characteristics
• CPC Class Codes: G06V 10/245 by locating a pattern; Special marks for positioning
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/418 Document matching, e.g. of document images
• CPC Class Codes: G06V 30/424 Postal images, e.g. labels or addresses on parcels or postal envelopes
• CPC Class Codes: H04L 9/3247 involving digital signatures

Abstract

An automated document processing machine may comprise an electro-mechanical transport subsystem configured to convey a document through the machine, and a camera arranged adjacent the transport and configured to capture an image of a front side of the document. A fingerprinting software component may be configured for processing the captured image of the document to create a unique digital fingerprint of the document based on the front side image, and a software interface may be configured for storing the digital fingerprint in a database of document identifiers in association with a unique alphanumeric identifier so that the document may be subsequently identified in a second processing machine that has access to the database. The digital fingerprint may be responsive to indicia that otherwise appears on the front side of the document, and may comprise data that identifies a document as being unique based on the front side indicia.

Claims

1. A method, comprising:

capturing a first digital image of a physical object;

parsing the digital image into at least one region of interest;

extracting identifying information from the region of interest, the identifying information including at least one feature of the region of interest;

combining the at least one feature for each region of interest to form a digital fingerprint of the object;

storing the digital fingerprint in a database, wherein the database comprises a plurality of digital fingerprints each associated with a corresponding physical object;

subsequently, obtaining a second digital image of a second physical object;

parsing the second image into at least one region of interest of the second object;

extracting identifying information from the region of interest, the identifying information including at least one feature of the region of interest of the second object;

combining the at least one feature for each region of interest to form a digital fingerprint of the second object;

comparing the digital fingerprint of the second object to the digital fingerprints stored in the database; and

responsive to the comparison, return an indication as to whether the second object is the first object.

2. The method of claim 1 wherein the feature is identified by location in the image;

and the feature location is stored in the database in relation to the digital fingerprint.

3. The method of claim 1 including selecting the region of interest based on relatively high variability of image information in that region among different instances of physical objects like the physical object.

4. The method of claim 1 including selecting a region of interest based on pre-defined regions of interest for the type of the physical object.

5. The method of claim 1 wherein the digital fingerprint comprises a defined pattern of multiple features extracted from the image.

6. The method of claim 5 wherein the pattern of features is pre-defined for the regions of interest for the type of the physical object.

7. The method of claim 5 wherein the pattern of features is user-defined.

8. The method of claim 5 wherein the defined pattern of features includes information on how to apply the pattern either alone or in a defined and prioritized order with other defined patterns.

9. The method of claim 5 wherein the defined pattern of features specifies what generic and specific information to return in response to the comparison step.

10. The method of claim 1 wherein the comparing of digital fingerprints includes comparison of individual elements and combining the results of comparisons of individual elements.

11. The method of claim 1 wherein the indication as to whether the second object is the first object is based on a deterministic threshold range, probabilistic, or both.

12. The method of claim 1 wherein the indication is based on at least one of (a) image data associated with the object and (b) a virtual representation of the object.

13. The method of claim 1 wherein the document fingerprint defines a spatial relationship between one or more features, artifacts, and/or indicia appearing or existing on the physical object.

14. The method of claim 13 wherein the one or more features, artifacts, and/or indicia may be visual, textual, and/or audible in nature.

15. A method, comprising:

capturing a first digital image of a physical object;

parsing the digital image into at least one region of interest;

extracting identifying information from the region of interest, the identifying information including at least one feature located within the region of interest, wherein the feature naturally occurs on the physical object and is not added to it for purposes of identification;

combining the at least one feature for each region of interest to form a digital fingerprint of the object;

storing the digital fingerprint in a database, wherein the database comprises a plurality of digital fingerprints each associated with a corresponding physical object;

subsequently, obtaining a second digital image of a second physical object;

parsing the second image into at least one region of interest of the second object;

extracting identifying information from the region of interest, the identifying information including at least one feature of the region of interest of the second object;

querying the database to return digital fingerprint records that include at least one feature located in the same region of interest as the feature of the second object;

comparing the feature of the second object to the digital fingerprints returned in response to the querying step; and

responsive to the comparison, return an indication as to whether the second object is the first object.

16. The method of claim 15 wherein the features extracted from the first and second images for identification include surface scratches or other indicia that occur during manufacture, assembly, handling, or usage.

17. The method of claim 15 wherein the features extracted from the first and second images for identification include surface scratches or other indicia that occur as a subsidiary effect of an intentional process.

18. The method of claim 15 including selecting the feature based on relatively high variability of image information for that feature among different instances of the physical object.