METHODS, APPARATUS AND SYSTEM FOR IDENTIFYING A DOCUMENT

• US 20140149428A1
• Filed: 11/28/2012
• Published: 05/29/2014
• Est. Priority Date: 11/28/2012
• Status: Active Grant

• Current Assignee: SAP SE
• Original Assignee: SAP AG (SAP SE)
• Inventors: Hobbs, Godfrey, Rupp, Stefanie, Gustav, Axel
• Granted Patent: US 9,075,847 B2
• Time in Patent Office: Days
• US Class Current: 707/749
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/93 Document management systems

Abstract

A computerized method for identifying a document. A signature may be determined for a first document and compared with a signature for each of one or more additional documents. A document similarity score may be determined and one or more similar documents may be identified based on the document similarity score.

Claims

1. A computerized method for document processing, the method comprising:

obtaining one or more counts of remarkable characteristics of a first document and one or more counts of remarkable characteristics of a second document;

comparing at least one of the one or more counts of remarkable characteristics of the first document and at least one of one or more corresponding counts of remarkable characteristics of the second document; and

determining a document similarity score between the first and second document.

2. The computerized method of claim 1, wherein the second document is one of a plurality of stored documents and further comprising repeating the comparing and determining steps for each of one or more of the plurality of stored documents.

3. The computerized method of claim 2, further comprising identifying one or more of the plurality of stored documents based on one or more lowest document similarity scores, a lower similarity score corresponding to a higher similarity.

4. The computerized method of claim 1, further comprising determining the one or more counts of remarkable characteristics of the first document for each of a plurality of cells of the first document.

5. The computerized method of claim 1, wherein the one or more counts of remarkable characteristics of the first document and the one or more corresponding counts of remarkable characteristics of a second document are normalized values.

6. The computerized method of claim 1, further comprising determining and persistently storing the one or more counts of remarkable characteristics for each of a plurality of cells of one or more of the plurality of stored documents.

7. The computerized method of claim 1, further comprising normalizing and persistently storing the one or more counts of remarkable characteristics for each of one or more of the plurality of stored documents.

8. The computerized method of claim 1, wherein the comparing step further comprises selecting a cell of a plurality of cells of the first document as a base cell and determining an absolute value of a difference between a remarkable characteristic count of the base cell associated with the first document and a corresponding remarkable characteristic count of a base cell of the second document to determine a base cell similarity score.

15. The computerized method of claim 1, wherein said remarkable characteristic is a keypoint.

10. The computerized method of claim 9, further comprising repeating the selecting and determining the absolute value steps for each of a plurality of cells of the first document.

11. The computerized method of claim 10, wherein the determining the document similarity score step further comprises summing the determined absolute values.

12. The computerized method of claim 10, wherein the determining the absolute value step further comprises:

selecting a neighboring cell of the base cell associated with the first document; and

determining an absolute value of a difference between a remarkable characteristic count of the selected neighboring cell associated with the first document and a remarkable characteristic count of a corresponding neighboring cell of the second document to determine a neighbor cell similarity score.

13. The computerized method of claim 12, wherein the determining the document similarity score step further comprises summing the determined base cell similarity scores and one or more neighbor cell similarity scores.

14. The computerized method of claim 12, further comprising weighting each neighbor cell similarity score and wherein the determining the document similarity score step further comprises summing the determined base cell similarity scores and one or more weighted neighbor cell similarity scores.

16. A computerized method for document processing, the method comprising:

capturing an image of a printed document;

determining one or more counts of remarkable characteristics of the printed document;

comparing at least one of the one or more counts of remarkable characteristics of the first document and at least one of one or more corresponding counts of remarkable characteristics of a second document of a plurality of stored documents;

determining a document similarity score;

repeating the comparing and determining steps for each of the plurality of stored documents; and

identifying one or more of the plurality of stored documents corresponding to one or more lowest document similarity scores.

17. The computerized method of claim 16, further comprising obtaining one or more of the identified stored documents.

18. The computerized method of claim 17, further comprising providing a link to one or more of the identified stored documents.

19. Apparatus for document processing, the apparatus comprising:

a processor;

memory to store instructions that, when executed by the processor cause the processor to;

obtain one or more counts of remarkable characteristics of a first document and one or more counts of remarkable characteristics of a second document;

compare at least one of the one or more counts of remarkable characteristics of the first document and at least one of one or more corresponding counts of remarkable characteristics of the second document; and

determine a document similarity score between the first and second document.

20. A computer-readable medium embodying instructions that, when executed by a processor perform operations comprising:

obtaining one or more counts of remarkable characteristics of a first document and one or more counts of remarkable characteristics of a second document;

comparing at least one of the one or more counts of remarkable characteristics of the first document and at least one of one or more corresponding counts of remarkable characteristics of the second document; and

determining a document similarity score between the first and second document.