Document processing system control using document feature analysis for identification

• US 8,477,992 B2
• Filed: 04/25/2008
• Issued: 07/02/2013
• Est. Priority Date: 04/26/2007
• Status: Active Grant

• Current Assignee: Bell & Howell LLC (Böwe Systec AG)
• Original Assignee: Bell & Howell LLC (Böwe Systec AG)
• Inventors: Paul, Mark G., Boston, Michael G., Spitzig, Roger, Rawlings, David, Conard, Walter S.
• Primary Examiner(s): GORADIA, SHEFALI DINESH
• Application Number:
  US12/149,043
• Publication Number:
  US 20080267510A1
• Time in Patent Office: 1,894 Days
• Field of Search: 382/100, 382/101
• US Class Current: 382/101
• CPC Class Codes: G06V 20/80 Recognising image objects characterised by unique random patterns
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/186 by deriving mathematical or geometrical properties from the whole image
• CPC Class Codes: G07B 17/00467 Transporting mailpieces postal sorting B07C
• CPC Class Codes: G07B 2017/00443 Verification of mailpieces, e.g. by checking databases
• CPC Class Codes: G07B 2017/00491 Mail/envelope/insert handling system

Abstract

The present subject matter relates to controlling of mail processing equipment. More specifically, the present subject matter allows for unique recognition of a printed document from all other similar documents, without the inclusion of additional purposeful identifying marks, data or barcodes. A document processing system, such as an inserter, printer, postage meter, sorter or other document processing system is controlled based on document identification which does not depend on unique identifiers. Similarly if a document is identified with a unique identifying mark on the first page, the present subject matter allows for identification of each subsequent page in the document without requiring identifying marks on each page. The identification data is then used to control the processing of the printed document based upon the recognition and enables the performance of quality checks. Further, each subsequent page in the document, as part of a quality check, can be verified without requiring identifying marks on each page.

Claims

1. A mail processing system for uniquely identifying a plurality of documents having minutiae associated with each of the plurality of documents, the plurality of documents to be processed by mail processing equipment of the mail processing system, the system comprising:

an image extraction module configured to receive an image captured from a post-print representation of the plurality of documents and extract image minutiae from the captured image for each of the plurality of documents;

a minutiae data processing module configured to compare the minutiae extracted from an electronic file associated with each of the plurality of documents with the extracted image minutiae for uniquely identifying each of the plurality of documents; and

a control processor configured to execute mail processing instructions associated with each uniquely identified document processed by the mail processing equipment, wherein the minutiae and the image minutiae are a plurality of document characteristics, wherein;

the plurality of document characteristics are selected from a combination of two or more of font, pitch, key word, numerical sequence, symbol, phrase and coordinates of an area of interest on the document,

the document characteristics individually are insufficient to uniquely identify one of the plurality of documents from a second document, but the combination of the two or more document characteristics are sufficient to uniquely identify the one document from the second document, and

the mail processing system is either an inserter system or sorter system.

2. The mail processing control system of claim 1, wherein the minutiae is stored in a database.

3. The mail processing system of claim 2, wherein the database is electronic data searchable by a computer.

4. The mail processing system of claim 2, wherein the database is configured to store the extracted minutiae for each document in a searchable format.

5. The mail processing system of claim 1, further comprising:

an electronic extraction module configured to extract the minutiae from a printed representation of the plurality of documents.

6. The mail processing system of claim 5, wherein the electronic extraction module is configured to extract minutiae from either:

a document composition phase of the document that defines the layout, format and content of the document;

or

a print file format which is used to control the printing of the document.

7. The mail processing system of claim 1, wherein each document is comprised of at least one sheet having printed material on one or both sides of the sheet.

8. The mail processing system of claim 1, wherein the captured image is captured by way of an image device coupled to the image extraction module.

9. The system of claim 1, wherein the minutiae data processing module is configured to perform one or more quality checks.

10. The system of claim 9, wherein the quality checks are selected from page count verification for each document, document sequence verification, and confirmation that printed documents were processed with correct mail processing equipment.

11. The system of claim 9, wherein the minutiae data processing module is configured to perform the one or more quality checks on at least one of the plurality of documents by comparing the extracted image minutiae from one or more pages of the document with corresponding minutiae associated with the document saved in a database.

12. The mail processing control system of claim 1, wherein the minutiae and the image minutiae are a plurality of document characteristics selected from font, pitch, key word, numerical sequence, symbol and phrase.

13. A method of controlling mail processing equipment of a mail processing system used to process one document of a plurality of documents, the one having minutiae extracted from an electronic file associated with the document, the method comprising the following steps:

processing a printed representation of the document on mail processing equipment, the processing including at least capturing of an image of the printed representation of the document;

extracting image minutiae from the captured image;

comparing the image minutiae with the minutiae for positively identifying the document; and

utilizing control data associated with the document to control operation of the mail processing equipment in response to positively identifying the document, wherein;

the minutiae and the image minutiae are a plurality of document characteristics, the plurality of document characteristics are selected from a combination of two or more of font, pitch, key word, numerical sequence, symbol, phrase and coordinates of an area of interest on the document,

the document characteristics individually are insufficient to uniquely identify the document from a second document, but the combination of the two or more document characteristics are sufficient to uniquely identify the one document from the second document, and

the mail processing system is either an inserter system or sorter system.

14. The method of claim 13, wherein the minutiae is obtained from either:

a document composition phase of the document that defines the layout, format and content of the document;

or

a print file format which is used to control the printing of the document.

15. The method of claim 13, wherein the capturing includes using an image device for image capturing.

16. The method of claim 13, wherein the processing step includes capturing an image of one or more sheets of the printed representation of the document.

17. A system configured to execute the steps of claim 13.

18. A non-transitory computer readable medium embodying a program, wherein execution of the program causes a computer to implement the method of claim 13.

19. The method of claim 13, wherein the minutiae and the image minutiae are a plurality of document characteristics selected from font, pitch, key word, numerical sequence, symbol and phrase.

20. A method of controlling a mail processing system comprising:

defining a super set of minutiae associated with each of a plurality of documents prior to processing on mail processing equipment of the mail processing system, the super set of minutiae including a plurality of minutiae candidates associated with each document which, in combination, provide positive identification of each document;

generating a document minutiae database for storing the plurality of minutiae candidates extracted from an electronic file;

obtaining control data associated with each document by matching the stored minutiae candidates for each document with image minutiae obtained from an image post-print representation of each document loaded on the mail processing equipment, and

applying the control data to control the operation of the mail processing equipment, wherein;

the stored minutiae and the image minutiae are a plurality of document characteristics, the plurality of document characteristics are selected from a combination of two or more of font, pitch, key word, numerical sequence, symbol, phrase and coordinates of an area of interest on the document, the document characteristics individually are insufficient to uniquely identify one of the plurality of documents from a second document, but the combination of the two or more document characteristics are sufficient to uniquely identify the one document from the second document, and

the mail processing system is either an inserter system or sorter system.

21. The method of claim 20, wherein the applying step includes applying the control data to control operation of document mail processing equipment selected from the group consisting of an inserter, printer, postage meter and sorter.

22. The method of claim 20, further comprising the step of assigning a search priority to the super set of minutiae by defining an order in which the minutiae candidates will be searched in the minutiae database.

23. The method of claim 20, wherein the generating step includes extracting minutiae from one or more sheets of the document.

24. A system configured to execute the steps of claim 20.

25. A non-transitory computer readable medium embodying a program, wherein execution of the program causes a computer to implement the method of claim 20.

26. The method of claim 20, wherein the obtaining step further includes obtaining control data from a minutiae data processing module.

27. The method of claim 20, wherein the obtaining step further includes obtaining control data from an inserter control computer.

28. The method of claim 20, wherein the minutiae and the image minutiae are a plurality of document characteristics selected from font, pitch, key word, numerical sequence, symbol and phrase.

29. A method of performing a quality check of a previously identified document (“

document”

) including a plurality of pages, the method comprising steps of;

capturing an image of a printed representation of the document processed on mail processing equipment of a mail processing system selected from an inserter or sorter system, the image including image minutiae for one or more pages of the document;

comparing minutiae associated with at least one page of the document which is subsequent to a first page of the document with associated image minutiae;

verifying that the at least one page of the document is part of the document; and

processing the document based on a result of the verifying step, wherein;

the minutiae extracted from an electronic file and the image minutiae are a plurality of document characteristics, the plurality of document characteristics are selected from a combination of two or more or font, pitch, key word, numerical sequence, symbol, phrase and coordinates of an area of interest on the document, the document characteristics individually are insufficient to uniquely identify the document, but the combination of the two or more document characteristics are sufficient to uniquely identify the document.

30. The method of claim 29, wherein at least the first page of the document includes a unique identifier selected from a postal authority barcode, sequence number or a mail processing system control code for unique identification of the document.

31. The method of claim 29, wherein the verifying step comprises confirming the at least one page is in sequential order in the document.

32. The method of claim 29, wherein the processing step includes any necessary corrective action.

33. The method of claim 29, wherein the minutiae and the image minutiae are a plurality of document characteristics selected from font, pitch, key word, numerical sequence, symbol and phrase.