Systems, methods and computer program products for determining document validity

• US 9,342,741 B2
• Filed: 12/31/2014
• Issued: 05/17/2016
• Est. Priority Date: 02/10/2009
• Status: Active Grant

• Current Assignee: Tungsten Automation Corp.
• Original Assignee: Kofax Incorporated
• Inventors: Amtrup, Jan W., Thompson, Stephen Michael
• Primary Examiner(s): MARIAM, DANIEL G
• Application Number:
  US14/588,147
• Publication Number:
  US 20150110362A1
• Time in Patent Office: 503 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 40/00 Handling natural language data speech analysis or synthesis, speech recognition G10L
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G06V 30/224 of printed characters having additional code marks or containing code marks
• CPC Class Codes: G06V 30/40 Document-oriented image-based pattern recognition
• CPC Class Codes: G06V 30/416 Extracting the logical structure, e.g. chapters, sections or page numbers; Identifying elements of the document, e.g. authors
• CPC Class Codes: H04N 1/40 Picture signal circuits H04N1/387 takes precedence

Abstract

According to one embodiment, a method includes: capturing an image of a financial document using a camera of a mobile device; performing optical character recognition (OCR) on the image of the financial document; extracting an identifier of the financial document from the image based at least in part on the OCR; associating the image of the financial document with metadata descriptive of one or more of the financial document and financial information relating to the financial document; and storing the image of the financial document and the associated metadata to a memory of the mobile device. Exemplary systems and computer program products are also disclosed.

Claims

1. A method, comprising:

capturing an image of a document using a camera of a mobile device;

classifying the image as an image of a financial document, the classifying further comprising;

generating a first representation of the image, the first representation being characterized by a reduced resolution;

generating a first feature vector based on the first representation;

comparing the first feature vector to a plurality of reference feature matrices; and

classifying an object depicted in the image as a member of a particular object class based at least in part on the comparing;

determine one or more object features of the object based at least in part on the particular object class;

performing optical character recognition (OCR) on the image of the financial document;

extracting an identifier of the financial document from the image based at least in part on the OCR;

associating the image of the financial document with metadata descriptive of one or more of the financial document and financial information relating to the financial document; and

storing the image of the financial document and the associated metadata to a memory of the mobile device.

2. The method as recited in claim 1, wherein the metadata comprise one or more of:

the identifier;

an account number associated with the financial document;

a financial service entity associated with the financial document;

a retailer associated with the financial document;

a name of an individual associated with the financial document;

a date associated with the financial document;

a security code associated with the financial document;

a personal identification number (PIN) associated with the financial document;

an account balance associated with the financial document; and

a credit limit associated with the financial document.

3. The method as recited in claim 1, wherein the financial document is a gift card, and

wherein the identifier corresponds to one or more of a gift card account number, a gift card security code, a gift card expiration date, and a gift card issuing entity.

4. The method as recited in claim 1, wherein the identifier comprises a plurality of masked characters;

wherein the extracted identifier comprises no mask symbols; and

wherein extracting the identifier comprises one or more of;

restricting an OCR alphabet to exclude the mask symbols,

reformatting the extracted identifier; and

discarding character positions from the extracted identifier.

5. The method as recited in claim 1, further comprising at least one of:

detecting one or more OCR errors based at least in part on textual information from a complementary document;

detecting one or more OCR errors in the financial document using one or more predefined business rules;

detecting one or more OCR errors based at least in part on textual information from the complementary document and one or more of the predefined business rules;

correcting at least one detected OCR error in the financial document using one or more of the predefined business rules;

correcting at least one detected OCR error in the financial document using textual information from the complementary document;

correcting at least one detected OCR error in the financial document using textual information from the complementary document and one or more of the predefined business rules;

normalizing data from a complementary document using at least one of the predefined business rules;

normalizing data from the financial document using at least one of the predefined business rules; and

normalizing data from the financial document using textual information from the complementary document and at least one of the predefined business rules.

6. The method as recited in claim 5, wherein one or more of:

the textual information from the financial document; and

the OCR errors in the financial document comprise the extracted identifier, and

wherein the textual information from the complementary document corresponds to the extracted identifier.

7. The method as recited in claim 5, further comprising prompting a user for input relating to the financial document, wherein the prompting occurs at least partially in response to detecting the OCR errors,

wherein the user input relates to the extracted identifier, and

wherein the at least one of the detecting, the correcting, and the normalizing is based at least in part on the user input.

8. The method as recited in claim 7, further comprising receiving the user input via a mobile device, wherein the user input relates to at least one of:

the OCR errors, the textual information from the complementary document, the identifier, and the predefined business rules.

9. The method as recited in claim 5, wherein the complementary document comprises content of an electronic record in a database, and wherein the database further comprises financial information for an account corresponding to the financial document.

10. The method as recited in claim 5, wherein the textual information from the complementary document comprises an account balance corresponding to the financial document.

11. The method as recited in claim 1, wherein the classifying comprises generating a feature vector representative of characteristics of the image of the financial document, the characteristics comprising one or more of:

a minimum brightness in one or more color channels at a particular location;

a maximum brightness in one or more color channels at a particular location;

an average brightness in one or more color channels at a particular location;

a presence of a particular reference feature at a particular location of the financial document;

dimensions of the financial document;

an aspect ratio of the financial document;

a color profile of the financial document;

a pixel density of the financial document in one or more color channels; and

a black pixel density of the financial document.

12. The method as recited in claim 1, wherein the classifying further comprises:

generating a first feature vector representative of the financial document, based on analyzing the image; and

comparing the first feature vector to a plurality of reference feature matrices.

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

processing the image using processing parameters selected based in whole or in part on the image classification, wherein the processing is configured to emphasize the identifier.

14. The method as recited in claim 1, wherein the identifier consists of characters selected from a predefined alphabet, wherein the predefined alphabet consists of either numerals, alphabetic characters, or symbols;

and

wherein the identifier comprises one or more of;

a date;

an account number;

a routing number;

a security code;

an accountholder name;

an accountholder address;

a financial processing entity;

a validation code; and

a personal identification number (PIN).

15. The method as recited in claim 1, wherein the classifying is based at least in part on a hyperplane defined in an N-dimensional feature space.

16. The method as recited in claim 1, further comprising classifying the financial document according to one of a plurality of financial document classifications, wherein the plurality of financial document classifications comprise:

gift card;

credit card;

debit card; and

check.

17. The method as recited in claim 1, further comprising determining an identifier type based on the classifying, and

wherein the extracting is further based at least in part on the financial document classification.

18. The method as recited in claim 1, further comprising detecting an attempt to initiate a financial transaction using the financial document, and

determining whether the financial document is an eligible form of payment for the financial transaction in response to detecting the attempt to initiate the financial transaction.

19. The method as recited in claim 18, further comprising prompting a user to capture the image of the financial document in response to detecting the attempt to initiate the financial transaction.

20. The method as recited in claim 18, wherein the financial document determined to be an eligible form of payment for the financial transaction is one of a plurality of eligible forms of payment for the financial transaction,

wherein each of the plurality of eligible forms of payment for the financial transaction corresponds to a unique financial document among a plurality of financial documents.

21. The method as recited in claim 20, wherein determining the financial document is an eligible form of payment for the financial transaction is based on one or more predetermined ranking criteria selected from:

an account associated with the financial document having an expiration date later than a date the financial transaction attempt is initiated;

the financial document having been used to process a prior financial transaction with an entity also corresponding to the attempted financial transaction;

a frequency of use of some or all of the plurality of financial documents being greater than a minimum frequency of use threshold;

the frequency of use of some or all of the plurality of financial documents being less than a maximum frequency of use threshold;

a recency of use of some or all of the plurality of financial documents being more than a minimum recency threshold;

the recency of use of some or all of the plurality of financial documents being less than a maximum recency threshold;

a frequency of use of some or all of the plurality of financial documents in at least one financial transaction between a user and the entity corresponding to the attempted financial transaction; and

a recency of use of some or all of the plurality of financial documents in at least one financial transaction between the user and the entity corresponding to the attempted financial transaction.

22. The method as recited in claim 21, wherein the predetermined ranking criteria correspond to a predetermined window of time.

23. The method as recited in claim 21, further comprising determining the financial document is a preferred form of payment for the financial transaction based on the predetermined ranking criteria.

24. The method as recited in claim 23, further comprising suggesting the preferred form of payment to the user via a display of a mobile device;

receiving user input relating to the suggestion, and either;

designating the preferred form of payment for the financial transaction in response to the user input confirming the suggestion;

or

designating another form of payment for the financial transaction in response to the user input negating the suggestion.

25. The method as recited in claim 1, the classifying further comprising recognizing one or more financial document features selected from:

color profile, color scheme, subregion color profile; and

subregion color scheme.

26. The method as recited in claim 1, wherein the financial document is a gift card, and the method further comprising:

detecting an attempt to initiate a financial transaction, and, in response to detecting the attempt to initiate the financial transaction;

extracting the identifier of the gift card from the image based on the classifying, wherein the identifier consists of numerals, and comprises one or more of an account number and a security code;

determining the financial document is one or more of an eligible form of payment for the financial transaction and a preferred form of payment for the financial transaction, the determining being based on a plurality of predetermined ranking criteria selected from;

an account associated with the financial document having a balance greater than or equal to a value of the financial transaction;

the account associated with the financial document having a credit limit greater than or equal to the value of the financial transaction;

the account associated with the financial document having an available credit amount greater than or equal to the value of the financial transaction;

the account associated with the financial document having an expiration date later than a date the financial transaction attempt is initiated;

the account associated with the financial document having associated therewith one or more of a benefit and a reward;

identifying data associated with the financial document matching identifying data provided in connection with the attempt to initiate the financial transaction;

the financial document having been used to process a prior financial transaction with an entity also corresponding to the attempted financial transaction

a frequency of use of some or all of a plurality of financial documents being greater than a minimum frequency of use threshold;

the frequency of use of some or all of the plurality of financial documents being less than a maximum frequency of use threshold;

a recency of use of some or all of the plurality of financial documents being more than a minimum recency threshold;

the recency of use of some or all of the plurality of financial documents being less than a maximum recency threshold;

a frequency of use of some or all of the plurality of financial documents in at least one financial transaction between a user and the entity corresponding to the attempted financial transaction; and

a recency of use of some or all of the plurality of financial documents in at least one financial transaction between the user and the entity corresponding to the attempted financial transaction;

suggesting the preferred form of payment to a user via a display of a mobile device;

prompting the user for input relating to the financial transaction;

receiving user input relating to the suggestion, and either;

designating the preferred form of payment for the financial transaction in response to the user input confirming the suggestion;

or

designating another form of payment for the financial transaction in response to the user input negating the suggestion.

27. A system, comprising:

a processor configured to execute logic;

the logic comprising;

logic configured to capture an image of a document using a camera of a mobile device;

logic configured to classify the image as an image of a financial document, the classifying further comprising;

generating a first representation of the image, the first representation being characterized by a reduced resolution;

generating a first feature vector based on the first representation;

comparing the first feature vector to a plurality of reference feature matrices; and

classifying an object depicted in the image as a member of a particular object class based at least in part on the comparing;

determine one or more object features of the object based at least in part on the particular object class;

logic configured to perform optical character recognition (OCR) on the image of the financial document;

logic configured to extract an identifier of the financial document from the image based at least in part on the OCR;

logic configured to associate the image of the financial document with metadata descriptive of one or more of the financial document and financial information relating to the financial document; and

logic configured to store the image of the financial document and the associated metadata to a memory of the mobile device.

28. A computer program product comprising:

a non-transitory computer readable medium having stored thereon computer readable program instructions, the computer readable program instructions comprising;

computer readable program instructions configured to capture an image of a document using a camera of a mobile device;

computer readable program instructions configured to classify the image as an image of a financial document, the classifying further comprising;

generating a first representation of the image, the first representation being characterized by a reduced resolution;

generating a first feature vector based on the first representation;

comparing the first feature vector to a plurality of reference feature matrices; and

classifying an object depicted in the image as a member of a particular object class based at least in part on the comparing;

determine one or more object features of the object based at least in part on the particular object class;

computer readable program instructions configured to perform optical character recognition (OCR) on the image of the financial document;

computer readable program instructions configured to extract an identifier of the financial document from the image based at least in part on the OCR;

computer readable program instructions configured to associate the image of the financial document with metadata descriptive of one or more of the financial document and financial information relating to the financial document; and

computer readable program instructions configured to store the image of the financial document and the associated metadata to a memory of the mobile device.