Methods and systems for processing documents

• US 9,384,391 B2
• Filed: 10/03/2014
• Issued: 07/05/2016
• Est. Priority Date: 10/03/2014
• Status: Active Grant

• Current Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Original Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Inventors: Gopalakrishnan, Sainarayanan, Kanagasabai, Rajasekar, Doss, Vignesh, Subbaian, Sudhagar, Li, Xing
• Primary Examiner(s): Chawan, Sheela C
• Application Number:
  US14/505,517
• Publication Number:
  US 20160098596A1
• Time in Patent Office: 641 Days
• Field of Search: 382/224, 382/183, 382/174, 382/100, 382/105, 382/168, 382/173, 382/181, 382/190, 382/199, 382/232, 382/254, 382/321, 382/276, 382/309
• US Class Current: 1/1
• CPC Class Codes: G06F 40/106 Display of layout of documents; Previewing
• CPC Class Codes: G06V 10/225 based on a marking or identifier characterising the area
• CPC Class Codes: G06V 30/36 Matching; Classification
• CPC Class Codes: G06V 30/413 Classification of content, e.g. text, photographs or tables

Abstract

Methods and systems for classifying a region of interest in an electronic document. A first region from the electronic document is extracted. The first region includes at least the region of interest. A first projection profile of pixels is determined in the region of interest. The first projection profile of pixels is indicative of a presence of a content in the region of interest. The region of interest is classified in at least one category based on a comparison of the first projection profile with a predetermined projection profile associated with the region of interest.

Claims

1. A method for classifying a region of interest in an electronic document, the method comprising:

extracting, by one or more processors, a first region from said electronic document, wherein said first region includes said region of interest and a tolerance region, wherein said tolerance region corresponds to a pre-defined area along a boundary of said region of interest;

determining, by said one or more processors, a first projection profile of pixels in said region of interest, wherein said first projection profile is indicative of a presence of a content in said region of interest; and

classifying, by said one or more processors, said region of interest in at least one category based on a comparison of said first projection profile with a predetermined projection profile associated with said region of interest.

2. The method of claim 1, wherein said at least one category corresponds to a manual extraction of said content from said region of interest or an automated extraction of said content from said region of interest.

3. The method of claim 2 further comprising transmitting, by said one or more processors, said classified region of interest to a user for said manual extraction based on the classification.

4. The method of claim 3 further comprising notifying, by said one or more processors, a user when a predetermined number of said region of interests in said electronic document are classified for said manual extraction.

5. The method of claim 1, wherein said first region is extracted based at least on a first set of co-ordinates associated with said region of interest, said tolerance region, and a second set of co-ordinates associated with a signature region, wherein said signature region is associated with said region of interest based on an association between said first set of co-ordinates and said second set of co-ordinates.

6. The method of claim 5 further comprising determining, by said one or more processors, a second projection profile of pixels in said tolerance region, wherein said second projection profile is indicative of a presence of a spill over content, associated with said content in said region of interest, in said tolerance region.

7. The method of claim 6 further comprising modifying said tolerance region in said first region, by said one or more processors, when said spill over content is present in said tolerance region, based on a comparison of a third projection profile associated with a modified first region and said predetermined projection profile, wherein said modified first region comprises said region of interest and said modified tolerance region.

8. The method of claim 6 further comprising modifying, by said one or more processors, said first set of co-ordinates associated with said region of interest based on said association between said first set of co-ordinates and said second set of co-ordinates.

9. The method of claim 8 further comprising extracting, by said one or more processors, said content from a modified first region, wherein said modified first region comprises at least one of a modified tolerance region or said modified first set of co-ordinates.

10. The method of claim 9, wherein said content is extracted using at least one of optical character recognition or intelligent character recognition.

11. The method of claim 1 further comprising notifying, by said one or more processors, a user about said presence of said content in said region of interest.

12. A system for classifying a region of interest in an electronic document, the system comprising:

one or more processors operable to;

extract a first region from said electronic document, wherein said first region includes said region of interest and a tolerance region, wherein said tolerance region corresponds to a pre-defined area along a boundary of said region of interest;

determine a first projection profile of pixels in said region of interest, wherein said first projection profile is indicative of a presence of a content in said region of interest; and

classify said region of interest in at least one category based on a comparison of said first projection profile with a predetermined projection profile associated with said region of interest.

13. The system of claim 12, wherein said at least one category corresponds to a manual extraction of said content from said region of interest or an automated extraction of said content from said region of interest.

14. The system of claim 13, wherein said one or more processors are further operable to transmit said classified region of interest to a user for said manual extraction based on the classification.

15. The system of claim 14, wherein said one or more processors are further operable to notify a user when a predetermined number of said region of interests in said electronic document are classified for said manual extraction.

16. The system of claim 12, wherein said first region is extracted based at least on a first set of co-ordinates associated with said region of interest, said tolerance region, and a second set of coordinates associated with a signature region, wherein said signature region is associated with said region of interest based on an association between said first set of co-ordinates and said second set of co-ordinates.

17. The system of claim 16, wherein said one or more processors are further operable to determine a second projection profile of pixels in said tolerance region, wherein said second projection profile is indicative of a presence of a spill over content, associated with said content in said region of interest, in said tolerance region.

18. The system of claim 17, wherein said one or more processors are further operable to modify said tolerance region, when said spill over content is present in said tolerance region based on a comparison of a third projection profile associated with a modified first region and said predetermined projection profile, wherein said modified first region comprises said region of interest and said modified tolerance region.

19. The system of claim 17, wherein said one or more processors are further operable to modify said first set of coordinates associated with said region of interest based on said association between said first set of co-ordinates and said second set of coordinates.

20. The system of claim 19, wherein said one or more processors are further operable to extract said content from a modified first region, wherein said modified first region comprises at least one of a modified tolerance region or said modified first set of co-ordinates.

21. The system of claim 20, wherein said content is extracted using at least one of optical character recognition or intelligent character recognition.

22. The system of claim 12, wherein said one or more processors are further operable to notify a user about said presence of said content in said region of interest.

23. A computer program product for use with a computer, the computer program product comprising a non-transitory computer readable medium, wherein the non-transitory computer readable medium stores a computer program code for classifying a region of interest in an electronic document, wherein the computer program code is executable by one or more processors to:

extract a first region from said electronic document, wherein said first region includes said region of interest and a tolerance region, wherein said tolerance region corresponds to a pre-defined area along a boundary of said region of interest;

determine a first projection profile of pixels in said region of interest, wherein said first projection profile is indicative of a presence of a content in said region of interest; and

classify said region of interest in at least one category based on a comparison of said first projection profile with a predetermined projection profile associated with said region of interest.