AUTOMATIC DOCUMENT SEPARATION

• US 20140164914A1
• Filed: 02/14/2014
• Published: 06/12/2014
• Est. Priority Date: 12/19/2003
• Status: Active Grant

• Current Assignee: Kofax Incorporated
• Original Assignee: Kofax Incorporated
• Inventors: Schmidtler, Mauritius A.R., Texeira, Scott S., Harris, Christopher K., Samat, Sameer, Borrey, Roland G., Macciola, Anthony
• Granted Patent: US 9,910,829 B2
• Time in Patent Office: Days
• US Class Current: 715/247
• CPC Class Codes: G06F 40/10 Text processing natural language analysis G06F40/20; semantic analysis G06F40/30; processing or translation of natural language G06F40/40
• CPC Class Codes: G06V 30/40 Document-oriented image-based pattern recognition
• CPC Class Codes: H04N 1/32112 in a separate computer file, document page or paper sheet, e.g. a fax cover sheet H04N1/32122 takes precedence
• CPC Class Codes: H04N 2201/3225 of data relating to an image, a page or a document
• CPC Class Codes: H04N 2201/3243 of type information, e.g. handwritten or text document

Abstract

A method and system for delineating document and/or subdocument boundaries and identifying document and/or subdocument types, the method comprising: automatically generating at least one identifier for identifying which of a plurality of document and/or subdocument images belongs to which of a plurality of categories. The method and/or system optionally may include automatically categorizing a plurality of document and/or subdocument images into a plurality of predetermined categories in accordance with classification rules for said categories.

Claims

1-12. -12. (canceled)

13. A method of delineating document boundaries and identifying document types, the method comprising:

automatically generating at least one identifier for identifying which of a plurality of document images belongs to which of a plurality of categories; and

outputting at least one of the identifier(s) to one or more of a display and a memory.

14. The method of claim 13, further comprising automatically categorizing the plurality of document images into the plurality of predetermined categories in accordance with one or more classification rules for the categories.

15. The method of claim 13, wherein the at least one identifier comprises a computer-generated separation page which is inserted between document images to delineate images belonging to different ones of the plurality of categories.

16. The method of claim 13, wherein the at least one identifier comprises a computer-readable description that identifies a categorization sequence for the plurality of digital images in accordance with their categorization.

17. The method of claim 16, wherein the computer-readable description comprises an XML message.

18. The method of claim 13, wherein the at least one identifier comprises at least one computer-generated label that is electronically associated with at least one of the plurality of document images.

19. The method of claim 13, wherein the plurality of categories comprises at least two different form types used in a financial transaction.

20. The method of claim 19, wherein the plurality of categories further comprise first, middle and end page categories for each of the at least two different form types.

21. The method of claim 13, wherein the step of automatically categorizing comprises:

producing an output score for each document image; and

using a graph search algorithm to determine an optimum categorization sequence from a plurality of possible categorization sequences for the plurality of document images based on the output scores.

22. The method of claim 21, wherein the output scores represents a probability that each document image belongs to at least one respective category from the plurality of categories.

23. The method of claim 21, wherein the step of using a graph search algorithm comprises:

using a graph structure to calculate a total output score, based on the output scores for each of the plurality of document images, for each the possible categorization sequence; and

determining which categorization sequence yields the highest total output score.

24. The method of claim 13, wherein at least some of the document images comprise an entire page of a document

25. The method of claim 13, wherein at least some of the document images consist of a subdocument.

26. In a computer-based system, a method of delineating document boundaries and identifying document types, comprising:

automatically categorizing a plurality of subdocument images into a plurality of predetermined categories in accordance with classification rules for said categories;

automatically generating at least one identifier for identifying which of said plurality of subdocument images belongs to which of said at least two categories; and

outputting at least one of the identifier(s) to one or more of a display and a memory.

27. The method of claim 26, wherein said at least one identifier comprises a computer-generated separation page which is inserted between subdocument images to delineate images belonging to different ones of said plurality of categories.

28. The method of claim 26, wherein said at least one identifier comprises a computer-readable description that identifies a categorization sequence for said plurality of digital images in accordance with their categorization.

29. The method of claim 28, wherein said computer-readable description comprises an XML message.

30. The method of claim 26, wherein said at least one identifier comprises at least one computer-generated label that is electronically associated with at least one of said plurality of subdocument images.

31. The method of claim 26, wherein said plurality of categories comprises at least a portion of two different forms used in a financial transaction.

32. The method of claim 31, wherein said plurality of categories further comprise at least two different form types.

33. The method of claim 32, wherein said step of automatically categorizing comprises:

producing an output score for each subdocument image; and

using a graph search algorithm to determine an optimum categorization sequence from a plurality of possible categorization sequences for said plurality of subdocument images based on said output scores.

34. The method of claim 33, wherein said output scores represents a probability that each subdocument image belongs to at least one respective category from said plurality of categories.

35. The method of claim 33, wherein said step of using a graph search algorithm comprises:

using a graph structure to calculate a total output score, based on said output scores for each of said plurality of subdocument images, for each said possible categorization sequence; and

determining which categorization sequence yields the highest total output score.

36. A computer program product comprising a computer readable storage medium having embodied thereon computer readable program code executable by a processor to cause the processor to:

categorize a plurality of subdocument images into a plurality of predetermined categories in accordance with classification rules for said categories;

generate at least one identifier for identifying which of said plurality of subdocument images belongs to which of said at least two categories; and

output at least one of the identifier(s) to one or more of a display and a memory.