Systems and methods for identification document processing and business workflow integration

Patent metadata

Field	Value
Publication number	US-9483794-B2
Application number	US-201414220016-A
Country	US
Kind code	B2
Filing date	Mar 19, 2014
Priority date	Jan 12, 2012
Publication date	Nov 1, 2016
Grant date	Nov 1, 2016

Abstract

A method includes: capturing or receiving at least one image of one or more identity documents (IDs) using a mobile device; determining identifying information from one or more of the IDs; building an ID profile based on the identifying information; storing the ID profile to a memory of the mobile device; invoking a workflow configured to facilitate a business transaction; detecting a predetermined stimulus in the workflow, the stimulus relating to the business transaction; providing at least a portion of the ID profile to the workflow in response to detecting the predetermined stimulus; and driving at least a portion of the workflow using the provided portion of the ID profile. Related systems and computer program products are also disclosed.

First claim

What is claimed is:

1. A method, comprising
initiating a workflow;
receiving an image comprising an identity document (ID);
analyzing the image to identify a plurality of document features, each document feature corresponding to the document;
building a feature vector based on at least some of the plurality of document features, wherein the plurality of document features upon which the feature vector is based are image characteristics corresponding to a photographic or pictorial portion of the ID rather than textual information depicted on the ID;
determining the document is an ID based on the feature vector;
processing the image to generate data comprising one or more of:
identifying information from the ID; and
a portion of the image depicting the ID; and

submitting data to the workflow; and
driving at least a portion of the workflow using some or all of the data.

2. The method as recited in claim 1 , the workflow further comprising:
detecting a predetermined stimulus in the workflow, wherein the predetermined stimulus indicates the workflow requires the identifying information;
in response to detecting the predetermined stimulus, either:
automatically invoking a capture interface of the workflow; or
automatically invoking a capture interface of a mobile device hosting at least a portion of the workflow; and

capturing the image using the invoked capture interface.

3. The method as recited in claim 2 , wherein the predetermined stimulus comprises one or more of:
attempting an operation within the workflow, the operation relying on financial information of an entity corresponding to the ID; and
displaying a user interface comprising one or more fields configured to receive the financial information.

4. The method as recited in claim 1 , wherein the feature vector describes a spatial distribution of the plurality of document features upon which the feature vector is based.

5. The method as recited in claim 1 , wherein the feature vector describes a color profile of a portion of the image corresponding to some or all of the plurality of document features upon which the feature vector is based.

6. The method as recited in claim 1 , further comprising building an ID profile based at least in part on the data;
storing the ID profile; and
performing the portion of the workflow at least in part using the ID profile.

7. The method as recited in claim 5 , wherein the portion of the image depicts one or more of a photograph, a logo, an emblem, a seal, a hologram, and a watermark.

8. The method as recited in claim 6 , further comprising verifying the ID profile, wherein verifying the ID profile comprises:
calculating a hash sum of the ID profile; and
comparing the calculated hash sum with a hash sum stored in association with the ID profile.

9. The method as recited in claim 1 , wherein the feature vector describes a spatial distribution of text fields as depicted in the image.

10. The method as recited in claim 6 , wherein the ID profile comprises at least one ID identifier for each of a plurality of IDs;
wherein the ID profile comprises identifying information obtained from at least two of the plurality of IDs, and
the method further comprising verifying the ID profile based on identifying information generated based on the at least two IDs.

11. The method as recited in claim 1 , wherein the feature vector describes a spatial distribution of a plurality of lines as depicted in the image.

12. The method as recited in claim 1 , wherein the image characteristics comprise one or more of:
a border of the document; and
a shape of an object depicted on the document.

13. The method as recited in claim 6 , further comprising:
invoking at least one additional workflow in response to determining the ID profile comprises identifying information required by the at least one additional workflow; and
driving the at least one additional workflow based on identifying information in the ID profile.

14. The method as recited in claim 1 , wherein the image characteristics comprise a color profile of a portion of the document depicting at least some of the plurality of document features upon which the feature vector is based.

15. The method as recited in claim 12 , wherein the image characteristics comprise a pattern depicted on the document, and
wherein the pattern comprises biometric data selected from fingerprint characteristics, ocular characteristics, and facial structure.

16. The method as recited in claim 1 , wherein the ID comprises at least one multi-page document; and
wherein the multi-page document comprises at least a first page corresponding to a front side of the ID and a second page corresponding to a back side of the ID.

17. The method as recited in claim 6 , wherein the ID profile comprises identifying information for multiple individuals involved in a single event or transaction, and
wherein the workflow comprises synthesizing the ID profile from identifying information generated based on multiple IDs corresponding to the multiple individuals.

18. The method as recited in claim 2 , wherein the workflow comprises a tracking activity, and
wherein the predetermined stimulus comprises one or more of:
invoking an authentication interface; and
invoking a logout interface.

19. The method as recited in claim 1 , wherein the image characteristics comprise a pattern depicted on the document, and
wherein the pattern comprises a distribution of one or more of:
borders depicted in the document; and
boxes depicted in the document.

20. A method, comprising:
capturing or receiving at least one image of one or more documents using a mobile device;
determining at least one of the documents is an identity document (ID) at least in part using support-vector machine techniques, wherein determining the at least one of the documents is an ID comprises:
analyzing the image to identify a plurality of document features, each document feature corresponding to the document;
building a feature vector based on at least some of the plurality of document features; and

determining the document is an identity document (ID) based on the feature vector, wherein some or all of the plurality of document features upon which the feature vector is based comprise one or more image characteristics rather than textual information;
determining identifying information from one or more of the IDs;
building an ID profile based on the identifying information;
storing the ID profile to a memory of the mobile device;
invoking a workflow configured to facilitate a business transaction;
detecting a predetermined stimulus in the workflow, the stimulus relating to the business transaction and the stimulus indicating the workflow requires the identifying information;
providing at least a portion of the ID profile to the workflow in response to detecting the predetermined stimulus; and
driving at least a portion of the workflow using the provided portion of the ID profile.

21. A computer program product, comprising: a non-transitory computer readable storage medium having computer readable program code stored therein, the computer readable program code comprising instructions configured to cause a processor to:
capture or receive at least one image of one or more identity documents (IDs) using a mobile device;
determine identifying information from the one or more IDs based at least in part on:
analyzing the image to identify a plurality of document features, each document fe

Assignees

• Kofax Inc

Inventors

• Amtrup Jan W
• Kilby Steven
• Macciola Anthony

Classifications

• G06Q20/3276 Primary

  using a pictured code, e.g. barcode or QR-code, being read by the M-device · CPC title

• G06Q40/03

  Credit; Loans; Processing thereof · CPC title

• G06Q50/18

  Legal services · CPC title

• G06Q20/3223

  Realising banking transactions through M-devices · CPC title

• H04N1/00106

  using land mobile radio networks, e.g. mobile telephone · CPC title