DATA CAPTURE FROM MULTI-PAGE DOCUMENTS

• US 20100060947A1
• Filed: 05/21/2009
• Published: 03/11/2010
• Est. Priority Date: 09/08/2008
• Status: Active Grant

• Current Assignee: ABBYY Development LLC
• Original Assignee: ABBYY Development LLC
• Inventors: Zlobin, Sergey, Filimonova, Irina, Tuganbaev, Diar
• Granted Patent: US 8,547,589 B2
• Time in Patent Office: Days
• US Class Current: 358/474
• 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 provided. The method comprises processing the scanned images into documents; for documents comprising multiple pages maintaining a page-based coordinate system to specify a location of structures within a page and joining the pages to form a multi-page sheet having a sheet-based coordinate system to specify a location of structures within the multi-page sheet; performing a data extraction operation to extract data from each document, said data extraction operation comprising 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 enabling a data capture system to capture data from a document image corresponding to a document, the method comprising:

defining a flexible structure description for the document, the flexible structure description comprising descriptions of structures in the document and detection information to facilitate detection of said structures in the document image, wherein the detection information specifies whether a structure is to be detected with reference to its placement within a page of the document, or with reference to its placement within the document as a whole; and

provisioning a data capture system with the flexible structure description.

2. The method of claim 1, wherein the flexible structure description comprises a minimum number of instances of a structure.

3. The method of claim 1, wherein the flexible structure description comprises a maximum number of instances of a structure.

4. The method of claim 2 or claim 3, wherein the instances are specified on a per page basis or on a per document basis.

5. The method of claim 1, wherein for a structure that spans more than one page, header information associated with the structure is described on a per page basis as a repetitive field in the flexible structure description.

6. The method of claim 1, wherein for a data field that spans several rows, said data field is represented as a repetitive field on a per document basis.

7. A data capture system, comprising:

a memory to store at least one flexible structure description, each corresponding to a document, said flexible structure description comprising descriptions of structures in the document and detection information to facilitate detection of said structures in a document image corresponding to the document, wherein the detection information specifies whether a structure is to be detected with reference to its placement within a page of the document, or with reference to its placement within the document as a whole; and

a processor to process scanned documents based on each flexible structure description.

8. The data capture system of claim 7, further comprising a scanner to acquire the scanned documents.

9. The data capture system of claim 7, wherein the flexible structure description comprises a minimum number of instances of a structure.

10. The data capture system of claim 7, wherein the flexible structure description comprises a maximum number of instances of a structure.

11. The data capture system of claim 9 or claim 10, wherein the instances are specified on a per page basis or on a per document basis.

12. The data capture system of claim 7, wherein for a structure that spans more than one page, header information associated with the structure is described on a per page basis as a repetitive field in the flexible structure description.

13. The data capture system of claim 7, wherein for a data field that spans several rows, said data field is represented as a repetitive field on a per document basis.

14. A method for processing a batch of scanned images, the method comprising:

processing the scanned images into documents;

for documents comprising multiple pages maintaining a page-based coordinate system to specify a location of structures within a page and joining the pages to form a multi-page sheet having a sheet-based coordinate system to specify a location of structures within the multi-page sheet;

performing a data extraction operation to extract data from each document, said data extraction operation comprising 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.

15. The method of claim 14, wherein processing the scanned images into documents comprises identifying the documents based header and footer information in predefined flexible structure descriptions.

16. The method of claim 14, wherein header information that spans more than one page is detected in page mode as a repetitive field.

17. The method of claim 16, wherein the header information is excluded from the data extraction operation.

18. The method of claim 16, wherein the header information is selected from the group consisting of table header information associated with a table, and a running title associated with a page.

19. The method of claim 14, wherein data in a table row is detected in document mode as a repetitive field that spans several rows.