Multi-page document recognition in document capture

Patent metadata

Field	Value
Publication number	US-2016335494-A1
Application number	US-201615221433-A
Country	US
Kind code	A1
Filing date	Jul 27, 2016
Priority date	Dec 19, 2012
Publication date	Nov 17, 2016
Grant date	—

Abstract

Techniques to capture document data are disclosed. It is determined that a sequence of pages in a stream of document page images comprise a single multi-page document. Data is extracted from two or more different pages included in the sequence. The data extracted from two or more different pages included in the sequence of pages is used to populate a data entry form associated with the multi-page document.

First claim

What is claimed is:

1 . A method of capturing document data, comprising:
obtaining a multi-page document from a sequence of pages; determining a document type based at least in part on the multi-page document and a data entry forms library; creating an instance of a type-specific data entry form based at least in part on the document type; populating the data entry form associated with the multi-page document based at least in part on the data associated with the multi-page document and the document type; identifying, according to one or more validation rules, one or more form fields for which validation of the corresponding data by a user is required based at least in part on data extracted from a plurality of pages associated with the multi-page document, wherein data extracted from a first page of the plurality of pages is dependent on data extracted from a second page of the plurality of pages; and providing, to the user, the one or more form fields for which validation of the corresponding data is required.

2 . The method of claim 1 , further comprising extracting data from two or more different pages included in the sequence.

3 . The method of claim 1 , wherein the identifying of the one or more form fields for which validation of the corresponding data by a user is required comprises validating a dependent data value according to one or more data values on which the dependent data value depends, wherein the one or more data values on which the dependent data value depends are extracted from a page of the multi-page document that is different from a page of the multi-page document from which the dependent data value is extracted.

4 . The method of claim 3 , wherein the one or more validation rules comprises confirming the dependent data value according to a defined dependency of the dependent data value on the one or more data values on which the dependent data value depends.

5 . The method of claim 3 , wherein the identifying the one or more form fields for which validation of the corresponding data by the user is required comprises:
determining whether the dependent data value matches another data value included in the multi-page document.

6 . The method of claim 3 , wherein the dependent data value and the one or more data values on which the dependent data value depends are comprised in a table or array of the multi-page document.

7 . The method of claim 3 , further comprising extracting data from two or more different pages included in the sequence, wherein the extracting data form two or more different pages included in the sequence comprises extracting the data values from pages comprising the multi-page document, and
wherein the data values extracted from the pages comprising the multi-page document are used to populate a single electronic data entry form.

8 . The method of claim 1 , wherein the providing of the one or more form fields to the user comprises:
providing a data validation interface that enables form fields comprising the data entry form to be validated.

9 . The method of claim 8 , wherein the validation interface enables an operator to iterate through the one or more form fields requiring validation.

10 . The method of claim 9 , wherein as each form field is displayed, a corresponding snippet or other partial image from a page from which a current data value associated with the form field was extracted is displayed adjacent to the field.

11 . The method of claim 10 , wherein as the operator iterates through fields associated with different pages, the corresponding snippet or other partial image is retrieved and displayed regardless of the source page within the multi-page document without requiring the operator to perform any other action to navigate to the corresponding page.

12 . The method of claim 1 , further comprising determining that a sequence of pages comprise the multi-page document.

13 . The method of claim 12 , wherein determining that a sequence of pages in a stream of document page images comprise a single multi-page document includes processing each page individually to determine a corresponding page type; and processing the stream of page types to identify a sequence associated with a multi-page document type.

14 . The method of claim 13 , wherein the document type contains one or more scalar fields and one or more tables of array fields.

15 . The method of claim 13 , further comprising extracting values from each page into per-page scalar and array fields by name.

16 . The method of claim 15 , wherein for each extracted value a corresponding location on the page from which the value was extracted is saved.

17 . The method of claim 15 , further comprising combining data extracted from the respective pages into a form associated with the document type.

18 . The method of claim 17 , wherein combining data extracted from the respective pages into a form associated with the document type includes for an array that spans multiple pages concatenating a first set of rows of values extracted from a first page with a second set of rows of values extracted from a second page to create a combined set of rows to be included in the document type.

19 . A document capture system, comprising:
a communication or other interface configured to receive a sequence of pages; and one or more processors coupled to the interface and configured to:
obtain a multi-page document from a sequence of pages;
determine a document type based at least in part on the multi-page document and a data entry forms library;
create an instance of a type-specific data entry form based at least in part on the document type;
populate the data entry form associated with the multi-page document based at least in part on the data associated with the multi-page document and the document type;
identify, according to one or more validation rules, one or more form fields for which validation of the corresponding data by a user is required, wherein identifying of the one or more form fields for which validation of the corresponding data by a user is required comprises validating a dependent data value according to one or more data values on which the dependent data value depends based at least in part on data extracted from a plurality of pages associated with the multi-page document, wherein data extracted from a first page of the plurality of pages is dependent on data extracted from a second page of the plurality of pages; and
provide, to the user, the one or more form fields for which validation of the corresponding data is required.

20 . A computer program product to capture document data, the computer program product being embodied in a non-transitory computer readable storage medium and comprising computer instructions for:
obtaining a multi-page document from a sequence of pages; determining a document type based at least in part on the multi-page document and a data entry forms library; creating an instance of a type-specific data entry form based at least in part on the document type; populating the data entry form associated with the multi-page document based at least in part on the data associated with the multi-page document and the document type; identifying, according to one or more validation rules, one or more form fields for which validation of the corresponding data by a user is required based at least in part on data extracted from a plurality of pages associated with the multi-page document, wherein data extracted from a first page of the pluralit

Assignees

• Emc Corp

Inventors

• Ho Ming Fung

Classifications

• G06V30/413

  Classification of content, e.g. text, photographs or tables · CPC title

• G06F40/226 Primary

  Validation · CPC title

• G06F40/174

  Form filling; Merging · CPC title

• G06V30/10

  Character recognition · CPC title

• G06K9/00469

  Physics · mapped topic