Systems and methods for identification document processing and business workflow integration

• US 9,058,515 B1
• Filed: 03/19/2014
• Issued: 06/16/2015
• Est. Priority Date: 01/12/2012
• Status: Active Grant

• Current Assignee: Kofax Incorporated
• Original Assignee: Kofax Incorporated
• Inventors: Ma, Jiyong, Kilby, Steven, Macciola, Anthony, Amtrup, Jan W.
• Primary Examiner(s): MARIAM, DANIEL G
• Application Number:
  US14/220,023
• Time in Patent Office: 454 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: H04N 1/387 Composing, repositioning or otherwise geometrically modifying originals
• CPC Class Codes: H04N 1/3872 Repositioning or masking
• CPC Class Codes: H04N 1/3878 Skew detection or correction

Abstract

A method involves: receiving an image comprising an ID; iteratively classifying the ID; and driving at least a portion of a workflow based at least in part on the classifying; wherein at least some of the classification iterations are based at least in part on comparing feature vector data, wherein a first classification iteration comprises determining the ID belongs to a particular class, and wherein each classification iteration subsequent to the first classification iteration comprises determining whether the ID belongs to a subclass falling within the particular class to which the ID was determined to belong in a prior classification iteration. Related systems and computer program products are also disclosed.

Claims

1. A method, comprising:

receiving or capturing an image comprising an identity document (ID) using a mobile device;

classifying the ID;

providing the ID and the ID classification to a workflow; and

driving at least a portion of the workflow based at least in part on the ID and the ID classification,

wherein the ID is one or more document(s) selected from a group consisting of;

a medical document;

a government-issued ID;

an employer-issued ID; and

an insurance document, and

wherein the classifying comprises;

determining the ID belongs a class of ID corresponding to driver'"'"'s licenses; and

determining the ID belongs to a subclass of driver'"'"'s licenses corresponding to a particular state, and

wherein driving the workflow is further driven at least in part based on the ID class and the ID subclass.

2. The method as recited in claim 1, wherein the classifying is based at least in part on comparing feature vector data, wherein the feature vector data corresponds to image characteristics and textual information.

3. The method as recited in claim 1, further comprising:

associating the ID classification with the image using a data-metadata relationship; and

storing the image and the associated ID classification to a memory of the mobile device.

4. The method as recited in claim 1, further comprising:

processing the image to identify each ID among a plurality of additional documents depicted in the image; and

classifying each of the identified IDs; and

analyzing each of the classified IDs based at least in part on the classification.

5. The method as recited in claim 1, further comprising:

analyzing the ID based at least in part on the classification; and

determining at least some identifying information from the ID based at least in part on one or more of;

a lookup operation utilizing the classification; and

a template corresponding to the classification.

6. The method as recited in claim 1, further comprising:

determining at least some identifying information from the ID, wherein the identifying information comprises one or more of;

biographical information;

geographic information

legal information; and

medical information.

7. The method as recited in claim 1, further comprising determining additional identifying information not depicted on the ID;

wherein driving the workflow is further based at least in part on at least some of the additional identifying information, and

wherein determining the additional identifying information is based at least in part on the ID class and the ID subclass.

8. The method as recited in claim 1, wherein the classifying is performed at least partially in response to detecting a predetermined stimulus in the business workflow.

9. The method as recited in claim 1, further comprising determining the ID corresponds to:

at least one human entity; and

at least one non-human entity.

10. The method as recited in claim 1, wherein the classifying does not rely on financial industry standards, the financial industry standards comprising:

a presence of one or more magnetic ink character recognition (MICR) characters;

a format of an account number; and

a format of a routing number.

11. The method as recited in claim 1, wherein, if the ID includes one or more medical documents, each medical document is selected from a group consisting of:

a chart;

a prescription; and

a genetic profile;

wherein, if the ID includes one or more government-issued IDs, each government-issued ID is selected from a group consisting of;

a driver'"'"'s license;

a hunting license;

a professional license;

a social security card;

a birth certificate;

a passport;

a military ID;

a tax form;

a social security card;

wherein, if the ID includes one or more employer-issued IDs, each employer-issued ID is selected from a group consisting of;

an employee identification card;

a security badge;

a certification; and

a benefits document.

12. The method as recited in claim 1, wherein classifying the ID comprises determining the ID corresponds to a type of document other than a financial document type.

13. The method as recited in claim 12, wherein the ID type corresponds to one or more of:

an authority issuing the ID;

an activity regulated in connection with the ID type; and

a geographic location corresponding to the ID type; and

wherein the method further comprises;

determining, based at least in part on the ID classification, the one or more of the issuing authority, the regulated activity, and the geographic location to which the ID type corresponds.

14. The method as recited in claim 1, further comprising:

classifying one or more elements of the ID; and

classifying the ID as a particular type of ID based at least in part on the element classification(s).

15. The method as recited in claim 1, wherein the classifying is performed at least in part using a processor of a mobile device.

16. A method, comprising:

receiving or capturing an image comprising an identity document (ID) using a mobile device;

classifying the ID; and

providing the ID and the ID classification to a workflow;

driving at least a portion of the workflow based at least in part on the ID and the ID classification;

analyzing the ID based at least in part on the ID classification;

determining at least some identifying information from the ID based at least in part on one or more of;

a lookup operation utilizing the classification; and

a template corresponding to the classification; and

at least one of building an ID profile and updating the ID profile, based at least in part on the analysis.

17. The method as recited in claim 16, further comprising submitting at least some data from the ID profile to the workflow.

18. The method as recited in claim 16, wherein the ID profile comprises a plurality of sub-profiles selected from:

a medical ID profile comprising medical identity information;

a financial ID profile comprising financial identity information; and

an employment ID profile comprising employee identity information.

19. A method, comprising:

receiving an image comprising an ID;

classifying the ID; and

driving at least a portion of a workflow based at least in part on the classifying;

wherein the classifying is based at least in part on comparing feature vector data, wherein the feature vector data are representative of;

image characteristics corresponding to the ID; and

textual information depicted on the ID,

wherein the classifying comprises;

determining the ID belongs a class of ID corresponding to driver'"'"'s licenses; and

determining the ID belongs to a subclass of driver'"'"'s licenses corresponding to a particular state, and

wherein the ID is one or more document(s) selected from a group consisting of;

a medical document;

a government-issued ID;

an employer-issued ID; and

an insurance document

wherein driving the workflow is further driven at least in part based on the ID class and the ID subclass.

20. A computer program product comprising:

a computer readable storage medium having computer readable program code stored therein, the computer readable program code comprising instructions configured to cause a processor to;

receive an image comprising an ID;

classify the ID, wherein the classifying comprises;

determining the ID corresponds to a type of document other than a financial document type; and

drive at least a portion of a workflow based at least in part on the ID classification;

wherein the classifying is an iterative process,

wherein each classification iteration subsequent to a first classification iteration is based at least in part on searching a subspace encompassed by a space searched in a prior classification iteration,

wherein the classifying is based at least in part on comparing feature vector data, and

wherein the feature vector data are representative of;

textual information depicted on the ID; and

image characteristics corresponding to the ID.

21. The computer program product as recited in claim 20, further comprising instructions configured to cause the processor to either:

identify at least one additional ID in the received image;

or

receive at least one additional image comprising one or more IDs and identify at least one additional ID in the additional image(s); and

iteratively classify the at least one additional ID;

analyze the at least one additional ID based at least in part on the classification; and

determine at least some identifying information from the at least one additional ID based at least in part on one or more of;

a lookup operation utilizing the classification; and

a template corresponding to the classification.

22. The computer program product as recited in claim 21, further comprising instructions configured to cause the processor to update an ID profile corresponding to one or more of the IDs based at least in part on the analysis.

23. The computer program product as recited in claim 22, further comprising instructions configured to cause the processor to submit at least some data from the updated ID profile to the workflow.