Data capture from multi-page documents

• US 8,538,162 B2
• Filed: 03/27/2012
• Issued: 09/17/2013
• Est. Priority Date: 09/08/2008
• Status: Expired due to Fees

• Current Assignee: ABBYY Development LLC
• Original Assignee: ABBYY Software
• Inventors: Tuganbaev, Diar, Skuratovskaya, Maryana, Zlobin, Sergey
• Primary Examiner(s): Haskins, Twyler
• Assistant Examiner(s): RODRIGUEZGONZALE, LENNIN R
• Application Number:
  US13/431,767
• Publication Number:
  US 20120183226A1
• Time in Patent Office: 539 Days
• Field of Search: None
• US Class Current: 382/195
• CPC Class Codes: H04N 1/00795 Reading arrangements details of scanning heads H04N1/024; scanning arrangements therefor H04N1/04
• CPC Class Codes: H04N 1/00803 Presence or absence of information
• CPC Class Codes: H04N 2101/00 Still video cameras
• CPC Class Codes: H04N 2201/3216 of a job size, e.g. a number of images, pages or copies, size of file, length of message

Abstract

A method for processing a batch of scanned images is disclosed. The method includes processing the scanned images into documents. For documents of multiple pages, the method maintains a page-based coordinate system to specify a location of structures within a page and joins the pages to form a multi-page sheet associated with a sheet-based coordinate system to specify a location of structures within the multi-page sheet. Data may be extracted from each document through a page mode wherein structures are detected on individual pages using the page-based coordinate system and a document mode wherein structures are detected within the entire document using the sheet-based coordinate system.

Claims

1. A method for creating a flexible structure description for a multi-page document, the method comprising:

acquiring electronic images of pages of at least one multi-page sample document;

determining a minimum number of pages to be used in creating the flexible structure description from the electronic images of pages of the at least one multi-page sample document;

determining a maximum number of pages to be used in creating the flexible structure description from the electronic images of pages of the at least one multi-page sample document;

identifying a first page for the flexible structure description from the multi-page sample document;

identifying a last page for the flexible structure description from the multi-page sample document;

from the at least one multi-page sample document, determining a range of pages in which an element of the multi-page document may be detected; and

storing information related to at least one of the minimum number of pages, the maximum number of pages, the first page identification, the last page identification, and the range of pages for one or more elements for the flexible structure description.

2. The method of claim 1, wherein the method further comprises determining a possible position in the first page for the element of the multi-page document.

3. The method of claim 1, wherein the method further comprises determining information identifying a location on one or more pages in which a repeating group of fields may be located in order to detect the repeating group of fields in images of pages from other multi-page documents.

4. The method of claim 3, wherein the repeating group of fields comprises one or more fields placed on one page with one or more additional fields placed on different page or different pages.

5. The method of claim 1, wherein the method further comprises determining information related to the element, the information describing the element'"'"'s possible placement on a document page.

6. The method of claim 1, wherein the method further comprises determining information related to the element, the information describing the element'"'"'s possible placement on pages of other multi-page documents.

7. The method of claim 1, wherein the maximum number of pages for the flexible structure description is determined from a plurality of multi-page sample documents, and wherein the maximum number of pages is equal to or greater than a maximum number of pages of any one of the multi-page sample documents.

8. The method of claim 1, wherein the flexible structure description comprises a maximum number of instances of the element that are capable of being detected in images of pages of other multi-page documents.

9. A data capture system, comprising:

an optical sensor;

a processor; and

a memory configured with processor-executable instructions which, when

executed by the processor, implement a method for creating a flexible structure description for a multi-page document, the method comprising;

acquiring electronic images of pages of a multi-page sample document;

identifying a first page for the flexible structure description from the multi-page sample document;

identifying a last page for the flexible structure description from the multi-page sample document;

from the multi-page sample document, determining a range of pages in which an element of the multi-page document may be detected in images of pages of other multi-page documents; and

electronically persisting in the memory the first page, the last page, and the range of pages for the element for the flexible structure description.

10. The data capture system of claim 9, wherein the instructions further cause the data capture system to:

determine a minimum number of pages for the flexible structure description from images of pages of the multi-page sample document; and

determine a maximum number of pages for the flexible structure description.

11. The data capture system of claim 9, wherein the instructions further cause the data capture system to:

determine a possible position for a first page for the element of the multi-page document.

12. The data capture system of claim 9, wherein the instructions further cause the data capture system to:

identify a location of one or more pages in which a repeating group of fields may be located in order to detect the repeating group of fields in images of pages from other multi-page documents.

13. The data capture system of claim 12, wherein the repeating group of fields comprises one or more fields placed on one page with one or more additional fields placed on a different page or pages, and wherein the instructions further cause the data capture system to:

determine an algorithm for finding instances of the repeating groups of fields in images of pages of other multi-page documents.

14. The data capture system of claim 9, wherein the instructions further cause the data capture system to:

determine information related to the element, the information describing the element'"'"'s possible placement within other multi-page documents.

15. The data capture system of claim 10, wherein the maximum number of pages for the flexible structure description is determined from a plurality of multi-page sample documents, and wherein the maximum number of pages is equal to or greater than a maximum number of pages of one of the multi-page sample documents.

18. The non-transitory computer-readable medium of claim 9, the method steps further comprising:

determining information identifying a location in document pages in which a repeating group of fields may be located when detecting the repeating group of fields in images of pages of other multi-page documents.

19. The non-transitory computer-readable medium of claim 18, wherein the repeating group of fields comprises one or more fields placed on one page with one or more additional fields placed on a different page or pages, and wherein the steps further comprising:

determining an algorithm for finding instances of the repeating groups of fields in images of pages of other multi-page documents.

16. A non-transitory computer-readable medium having stored thereon instructions, which when executed by a processing system, cause the processing system to implement steps to create a flexible structure description for a multi-page document, the steps comprising:

acquiring electronic images of pages of a multi-page sample document;

identifying a first page for the flexible structure description from the multi-page sample document;

identifying a last page for the flexible structure description from the multi-page sample document;

from the multi-page sample document, determining a range of pages in which an element of the multi-page document may be detected; and

electronically persisting in a storage an indication of the first page, the last page, and the range of pages for the element for the flexible structure description.

17. The non-transitory computer-readable medium of claim 16, wherein the steps further comprising:

determining a possible first page position for the element of the multi-page document where the element is capable of being detected in images of pages of other multi-page documents.