Global geographic information retrieval, validation, and normalization

• US 9,934,433 B2
• Filed: 08/24/2017
• Issued: 04/03/2018
• Est. Priority Date: 02/10/2009
• Status: Active Grant

• Current Assignee: Kofax Incorporated
• Original Assignee: Kofax Incorporated
• Inventors: Thompson, Stephen Michael, Amtrup, Jan W., Macciola, Anthony
• Primary Examiner(s): MARIAM, DANIEL G
• Application Number:
  US15/686,017
• Publication Number:
  US 20170351915A1
• Time in Patent Office: 222 Days
• Field of Search: 382112, 382218, 382313
• CPC Class Codes: G06F 16/2365 Ensuring data consistency and integrity
• CPC Class Codes: G06F 16/2468 Fuzzy queries
• CPC Class Codes: G06F 16/51 Indexing; Data structures therefor; Storage structures
• CPC Class Codes: G06F 16/5838 using colour
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/224 of printed characters having additional code marks or containing code marks
• CPC Class Codes: G06V 30/413 Classification of content, e.g. text, photographs or tables
• 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
• CPC Class Codes: H04N 1/40062 Discrimination between different image types, e.g. two-tone, continuous tone

Abstract

A computer program product includes program instructions configured to cause a processor, to: perform optical character recognition (OCR) on an image of a document; extract an identifier of the document from the image based at least in part on the OCR; compare at least portions of the identifier with content from one or more reference data sources; and determine whether the identifier is valid based at least in part on the comparison. The content comprises global address information; while the content from the reference is derived from geographic information. Deriving the content from the geographic information includes: obtaining the geographic information; and parsing the geographic information according to a set of predefined heuristic rules, where the heuristic rules are configured to normalize the global address information obtained from the one or more sources according to a single convention for representing address information.

Claims

1. A computer program product, comprising a non-transitory computer readable storage medium having stored/encoded thereon computer readable program instructions configured to cause a processor, upon execution thereof, to:

perform optical character recognition (OCR) on an image of a document;

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

compare at least portions of the identifier with content from one or more reference data sources; and

determine whether the identifier is valid based at least in part on the comparison;

wherein the content from the one or more reference data sources comprises global address information;

wherein the content from the one or more reference data sources is derived from geographic information organized in one or more of a proprietary address database and an open source address database; and

wherein deriving the content from the geographic information comprises;

obtaining the geographic information from one or more of the proprietary address database and an open source address database; and

parsing the geographic information according to a set of predefined heuristic rules, wherein the set of predefined heuristic rules are configured to normalize the global address information obtained from the one or more sources according to a single convention for representing address information.

2. The computer program product as recited in claim 1, wherein the identifier consists of characters selected from a predefined alphabet, wherein the predefined alphabet consists of one or more of numerals, alphabetic characters, and symbols.

3. The computer program product as recited in claim 1, wherein the identifier comprises a partial or complete address.

4. The computer program product as recited in claim 1, wherein the identifier comprises one or more of:

a street name, a street number, a block number, a unit number, a city name, a county name, a municipality name, a state name, a state abbreviation, a country name, a country abbreviation, and a ZIP code.

5. The computer program product as recited in claim 1, wherein comparing at least portions of the identifier with content from one or more reference data sources comprises fuzzy matching the identifier with the content from the one or more data sources.

6. The computer program product as recited in claim 1, wherein the identifier is validated based at least in part on determining a fuzzy match exists between the identifier and at least a portion of the global address information, wherein the fuzzy match is characterized by no more than two character mismatches between the identifier and at least the portion of the global address information.

7. The computer program product as recited in claim 1, comprising locating the identifier within the image based on a connected components analysis.

8. The computer program product as recited in claim 1, wherein the OCR is performed only on a portion of the image determined to depict the identifier.

9. The computer program product as recited in claim 1, comprising determining a locality associated with the identifier;

and

wherein the set of predefined heuristic rules are selected based on the locality determined to be associated with the extracted identifier.

10. The computer program product as recited in claim 1, wherein deriving the content from the geographic information comprises populating the one or more data sources with the content, wherein the content consists of geographic information parsed using the set of predefined heuristic rules.

11. The computer program product as recited in claim 1, wherein deriving the content from the geographic information comprises normalizing the geographic information to expand one or more abbreviations present in the geographic information;

and

wherein the content excludes abbreviated geographic information.

12. The computer program product as recited in claim 1, comprising normalizing the extracted identifier prior to comparing the identifier with content from one or more reference data sources, wherein the normalizing is performed according to one or more predefined business rules corresponding to a particular locality.

13. The computer program product as recited in claim 1, comprising determining a locality corresponding to the extracted identifier, and

retrieving additional geographic information associated with a location corresponding to the identifier based at least in part on the locality.

14. The computer program product as recited in claim 13, wherein determining the locality is based at least in part on one or more of a content and a format of the identifier.

15. The computer program product as recited in claim 13, wherein retrieving the additional geographic information is based at least in part on latitude and longitude coordinates corresponding to the identifier.

16. The computer program product as recited in claim 1, 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 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 using one or more of the predefined business rules;

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

correcting at least one detected OCR error 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 document using at least one of the predefined business rules; and

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

17. The computer program product as recited in claim 1, wherein the identifier comprises non-textual information depicted on the document.

18. The computer program product as recited in claim 1, wherein the identifier is encoded in non-textual information depicted on the document.

19. The computer program product as recited in claim 1, wherein the document is a financial document.

20. A computer program product, comprising a non-transitory computer readable storage medium having stored/encoded thereon computer readable program instructions configured to cause a processor, upon execution thereof, to:

capture an image using a camera of a mobile device;

classify the image as an image of a document, wherein the classifying comprises;

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

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

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

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

compare the identifier with content from one or more reference data sources;

determine whether the identifier is valid based at least in part on the comparison; and

in response to determining the identifier is valid;

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

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

wherein the content from the one or more reference data sources comprises global address information;

wherein the content from the one or more reference data sources is derived from geographic information organized in one or more of a proprietary address database and an open source address database; and

wherein deriving the content from the geographic information comprises;

obtaining the geographic information from one or more of the proprietary address database and an open source address database; and

parsing the geographic information according to a set of predefined heuristic rules, wherein the set of predefined heuristic rules are configured to normalize the global address information obtained from the one or more sources according to a single convention for representing address information.