Systems, methods and computer program products for determining document validity

• US 8,774,516 B2
• Filed: 11/12/2013
• Issued: 07/08/2014
• Est. Priority Date: 02/10/2009
• Status: Active Grant

• Current Assignee: Kofax Incorporated
• Original Assignee: Kofax Incorporated
• Inventors: Amtrup, Jan, Macciola, Anthony, Thompson, Steve
• Primary Examiner(s): TUCKER, WESLEY J
• Application Number:
  US14/078,402
• Publication Number:
  US 20140079294A1
• Time in Patent Office: 238 Days
• Field of Search: 382/181, 382/182, 382/209, 382/218, 382/305, 382/317, 382/321
• US Class Current: 382/182
• CPC Class Codes: G06F 2218/08 Feature extraction
• CPC Class Codes: G06Q 20/10 specially adapted for electronic funds transfer [EFT] systems; specially adapted for home banking systems
• CPC Class Codes: G06Q 20/3276 using a pictured code, e.g. barcode or QR-code, being read by the M-device
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/12 Detection or correction of errors, e.g. by rescanning the pattern
• CPC Class Codes: G06V 30/1448 based on markings or identifiers characterising the document or the area
• CPC Class Codes: G06V 30/224 of printed characters having additional code marks or containing code marks
• CPC Class Codes: G06V 30/2247 Characters composed of bars, e.g. CMC-7
• 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: G06V 30/418 Document matching, e.g. of document images

Abstract

In one embodiment, a method includes receiving an image of a document; performing optical character recognition (OCR) on the image; extracting an address of a sender of the document from the image based on the OCR; comparing the extracted address with content in a first database; identifying complementary textual information in a second database based on the address; and at least one of: extracting additional content from the image of the document; correcting one or more OCR errors in the document using the complementary textual information, and normalizing data from the document prior to determining a validity of the document using at least one of the complementary textual information and predefined business rules. At least one of the aforementioned operations is performed using a processor of a mobile device. Exemplary systems and computer program products are also disclosed.

Claims

1. A method, comprising:

receiving an image of a document;

performing optical character recognition (OCR) on the image;

extracting an address of a sender of the document from the image based on the OCR;

comparing the extracted address with content in a first database;

identifying complementary textual information in a second database based on the address; and

at least one of;

extracting additional content from the image of the document;

correcting one or more OCR errors in the document using the complementary textual information, and

normalizing data from the document prior to determining a validity of the document using at least one of the complementary textual information and predefined business rules,

wherein at least one of performing the OCR, extracting the address, comparing the extracted address, identifying the complementary textual information, extracting the additional content, correcting the one or more OCR errors and normalizing the data is performed using a processor of a mobile device.

2. The method as recited in claim 1, further comprising validating textual information in the document.

3. The method as recited in claim 1, further comprising correlating textual information from the document to textual information in a complementary document.

4. The method as recited in claim 3, wherein the complementary document comprises an electronic document in the second database.

5. The method as recited in claim 3, wherein the complementary document comprises an extraction template.

6. The method as recited in claim 1, further comprising updating text of the document, wherein the updating comprises correcting one or more of the OCR errors.

7. The method as recited in claim 1, further comprising determining whether the document is related to a complementary document.

8. The method as recited in claim 7, further comprising determining a confidence level of the determination of whether the document is related to the complementary document.

9. The method as recited in claim 1, wherein the one or more OCR errors comprise one or more of incorrectly identified characters and unidentified characters.

10. The method as recited in claim 1, wherein one or more of the comparing and the identifying comprises fuzzy matching.

11. The method as recited in claim 1, wherein extracting the address of the sender comprises scanning a barcode.

12. The method as recited in claim 1, wherein the complementary textual information corresponds to one or more fields of a complementary document.

13. The method as recited in claim 1, wherein the additional content comprises one or more of:

textual information in a format specific to the sender; and

non-textual information specific to the sender.

14. The method as recited in claim 1, wherein extracting the additional content utilizes one or more of:

an extraction template configured to facilitate template-based extraction; and

location information regarding the additional content.

15. A system, comprising:

a server having a server processor and logic in and/or executable by the server processor; and

a mobile device having a mobile device processor and logic in and/or executable by the mobile device processor;

wherein the logic is configured to cause one or more of the processors, singly or in combination, to;

receive an image of a document;

perform optical character recognition (OCR) on the image;

extract an address of a sender of the document from the image based on the OCR;

compare the extracted address with content in a first database;

identify complementary textual information in a second database based on the address; and

at least one of;

extract additional content from the image of the document;

correct one or more OCR errors in the document using the complementary textual information, and

normalize data from the document prior to determining a validity of the document using at least one of the complementary textual information and predefined business rules.

16. A method, comprising:

receiving an image of a part or all of a document selected from a group consisting of;

a gift card, an invoice, a bill, a receipt, a sales order, an insurance claim, a medical insurance document, and a benefits document;

performing optical character recognition (OCR) on the image;

extracting at least a partial address of a sender of the document;

comparing the at least partial address of the sender to a plurality of addresses in a first database; and

identifying one or more of;

textual information specific to the sender; and

data formatting specific to the sender,

wherein at least one of performing the OCR, extracting the at least partial address, and identifying one or more of the textual information and the data formatting specific to the sender is performed using a processor of a mobile device.

17. The method as recited in claim 16, further comprising validating textual information in the document.

18. The method as recited in claim 16, further comprising correlating textual information from the document to textual information in a complementary document.

19. The method as recited in claim 16, further comprising updating textual information of the document, wherein the updating comprises correcting one or more OCR errors in the textual information of the document.

20. The method as recited in claim 19, wherein the one or more OCR errors comprise one or more of incorrectly identified characters and unidentified characters.

21. The method as recited in claim 16, wherein one or more of the comparing and the identifying comprises fuzzy matching.

22. The method as recited in claim 16, wherein extracting the at least partial address comprises scanning a barcode.

23. The method as recited in claim 16, wherein the data formatting specific to the sender comprises one or more fields corresponding to fields of a complementary document.

24. The method as recited in claim 16, further comprising comparing one or more portions of the document to one or more portions of a complementary document, wherein the complementary document is at least one of:

an electronic document in a second database; and

an extraction template.

25. The method as recited in claim 16, further comprising:

determining whether the document is related to a complementary document.

26. The method as recited in claim 25, further comprising determining a confidence level of the determination of whether the document is related.

27. The method as recited in claim 16, wherein the data formatting specific to the sender comprises at least one of:

textual information in a format specific to the sender; and

non-textual information.

28. The method as recited in claim 16, further comprising extracting additional content from the image of the document.

29. The method as recited in claim 28, wherein extracting the additional content utilizes one of more of:

a template-based extraction technique; and

location information regarding the additional content.

30. A system, comprising:

a mobile device comprising a processor and logic in and/or executable by the processor to cause the processor to;

receive an image of a part or all of a document selected from a group consisting of;

a gift card, an invoice, a bill, a receipt, a sales order, an insurance claim, a medical insurance document, and a benefits document;

perform optical character recognition (OCR) on the image;

extract at least a partial address of a sender of the document;

compare the at least partial address of the sender to a plurality of addresses in a first database; and

identify one or more of;

textual information specific to the sender; and

data formatting specific to the sender,

wherein at least one of performing the OCR, extracting the at least partial address, and identifying one or more of the textual information and the data formatting specific to the sender is performed using the processor of the mobile device.