Comparing documents using a trusted source

Patent metadata

Field	Value
Publication number	US-9922247-B2
Application number	US-201514588670-A
Country	US
Kind code	B2
Filing date	Jan 2, 2015
Priority date	Dec 18, 2013
Publication date	Mar 20, 2018
Grant date	Mar 20, 2018

Abstract

Systems and methods for enhancing and comparing documents. An example method comprises: comparing document images to identify a first document image of a reference document that corresponds with a second document image of a related document; transforming the second document image based on a layout of the first document image; and performing character recognition of the second document image.

First claim

What is claimed is:

1. A method comprising:
performing document analysis of a first document image of a related document;
performing a first character recognition of the first document image;
comparing the first document image with a second document image of a reference document based on results of the first character recognition;
transforming the first document image based on the comparison of the first document image and the second document image; and
performing a second character recognition of the transformed first document image using a reference dictionary generated in view of the reference document.

2. The method of claim 1 , further comprising calculating differences between the related document and the reference document based on results of the second character recognition.

3. The method of claim 1 , wherein the comparing the first document image with the second document image comprises comparing at least a part of a first layout and at least a part of a first text produced by the first character recognition of the first document image to at least a part of a second layout and at least a part of a second text of the second document image.

4. The method of claim 3 , wherein the part of the first text and the part of the second text comprise words having at least a predefined number of characters, and wherein the comparing further comprises calculating an edit distance between corresponding words.

5. The method of claim 1 , wherein the first document image comprises an image of a page of a document.

6. The method of claim 1 , wherein transforming comprises performing a linear transformation of the second document image based on positions of three points within each of the first document image and the second document image.

7. The method of claim 1 , wherein the reference dictionary comprises words from only a specific text block of the second document image.

8. A system comprising:
a memory;
a processor coupled to the memory, the processor configured to:
perform document analysis of a first document image of a related document;
perform a first character recognition of the first document image;
compare the first document image with a second document image of a reference document based on results of the first character recognition;
transform the first document image based on the comparison of the first document image and the second document image; and
perform a second character recognition of the transformed first document image using a reference dictionary generated in view of the reference document.

9. The system of claim 8 , wherein the processor is further configured to calculate differences between the related document and the reference document based on results of the second character recognition.

10. The system of claim 8 , wherein comparing the first document image with the second document image comprises comparing at least a part of a first layout and at least a part of a first text produced by the first character recognition of the first document image to at least a part of a second layout and at least a part of a second text of the second document image.

11. The system of claim 10 , wherein the part of the first text and the part of the second text comprise words having at least a predefined number of characters, and wherein the comparing further comprises calculating an edit distance between corresponding words.

12. The system of claim 8 , wherein the first document image comprises an image of a page of a document.

13. The system of claim 8 , wherein transforming comprises performing a linear transformation of the second document image based on positions of three points within each of the first document image and the second document image.

14. The system of claim 8 , wherein the reference dictionary comprises words from only a specific text block of the second document image.

15. A computer-readable non-transitory storage medium comprising executable instructions that, when executed by a computing device, cause the computing device to perform operations comprising:
performing document analysis of a first document image of a related document;
performing a first character recognition of the first document image;
comparing the first document image with a second document image of a reference document based on results of the first character recognition;
transforming the first document image based on the comparison of the first document image and the second document image; and
performing a second character recognition of the transformed first document image using a reference dictionary generated in view of the reference document.

16. The computer-readable non-transitory storage medium of claim 15 , further comprising calculating differences between the related document and the reference document based on results of the second character recognition.

17. The computer-readable non-transitory storage medium of claim 15 , wherein comparing the first document image with the second document image comprises comparing at least a part of a first layout and a part of a first text produced by the first character recognition of the first document image to at least a part of a second layout and a part of a second text of the second document image.

18. The computer-readable non-transitory storage medium of claim 17 , wherein the part of the first text and the part of the second text comprise words having at least a predefined number of characters, and wherein the comparing further comprises calculating an edit distance between corresponding words.

19. The computer-readable non-transitory storage medium of claim 15 , wherein transforming comprises performing a linear transformation of the second document image based on positions of three points within each of the first document image and the second document image.

20. The computer-readable non-transitory storage medium of claim 15 , wherein the reference dictionary comprises words from only a specific text block of the second document image.

Assignees

• Abbyy Dev Llc

Inventors

• Khintsitskiy Ivan
• Isaev Andrey

Classifications

• G06K2209/01

  Physics · mapped topic

• G06K9/00483 Primary

  Physics · mapped topic

• G06V30/418 Primary

  Document matching, e.g. of document images · CPC title