Method and System for Creating a Form Template for a Form

• US 20090074303A1
• Filed: 08/27/2008
• Published: 03/19/2009
• Est. Priority Date: 09/14/2007
• Status: Active Grant

• Current Assignee: ABBYY Development LLC
• Original Assignee: ABBYY Software
• Inventors: Filimonova, Irina, Zlobin, Sergey
• Granted Patent: US 8,295,590 B2
• Time in Patent Office: Days
• US Class Current: 382/224
• CPC Class Codes: G06V 30/412 Layout analysis of documents structured with printed lines or input boxes, e.g. business forms or tables

Abstract

A method and system for creating a form template for a form are disclosed. The method comprises analyzing an image of a form to detect object demarcations in the form. The method also comprises classifying the object demarcations into one of a plurality of predefined object categories and processing each object demarcation based on the object category into which it has been classified, thereby to create the form template automatically.

Claims

1. A method of creating a form template for a form, the method comprising:

analyzing an image of the form to detect object demarcations on the form;

classifying the object demarcations into one of a plurality of predefined object categories; and

processing each object demarcation based on the object category into which it has been classified, thereby to create the form template automatically.

2. The method of claim 1, in which classifying the object demarcations comprises comparing the object demarcations against predefined object definitions.

3. The method of claim 1, in which processing each object demarcation comprises determining whether or not a particular object demarcation has other object demarcations associated therewith and, if so, grouping together the associated object demarcations.

4. The method of claim 3, in which determining whether or not a particular object demarcation has other object demarcations associated therewith comprises determining whether or not any similarly classified object demarcations are within a predefined distance thereof and, if so, grouping together the similarly classified object demarcations within the predefined distance.

5. The method of claim 3, in which determining whether or not a particular object demarcation has other object demarcations associated therewith comprises determining whether or not any similarly classified object demarcations are within a particular region on the image and, if so, grouping together the similarly classified object demarcations within the particular region.

6. The method of claim 4, in which:

a predefined object category comprises a preprinted character; and

grouping together the associated object demarcations comprises grouping preprinted characters into a word.

7. The method of claim 6, which comprises grouping words into a sentence.

8. The method of claim 4, in which:

a predefined object category comprises a character input field; and

grouping together the associated object demarcations comprises grouping character input fields into a text input field.

9. The method of claim 5, in which:

a predefined object category comprises a checkmark field; and

grouping together the associated object demarcations comprises grouping together checkmark fields in the particular region.

10. A system for creating a form template for a form, the system comprising a processor and application software operable to:

analyze an image of a form to detect object demarcations on the form;

classify the object demarcations into one of a plurality of predefined object categories; and

process each object, demarcation based on the object category into which it has been classified, thereby to create the form template automatically.

11. The system of claim 10, which is operable to compare the object demarcations against predefined object definitions, thereby to classify the object demarcations.

12. The system of claim 10, which is operable to determine whether or not a particular object demarcation has other object demarcations associated therewith and, if so, to group together the associated object demarcations, thereby to process each object demarcation.

13. The system of claim 12, which is operable to determine whether or not any similarly classified object demarcations are within a predefined distance thereof and, if so, to group together the similarly classified object demarcations within the predefined distance, thereby to determine whether or not a particular object demarcation has other object demarcations associated therewith.

14. The system of claim 12, which is operable to determine whether or not any similarly classified object demarcations are within a particular region on the image and, if so, to group together the similarly classified object demarcations within the particular region, thereby to determine whether or not a particular object demarcation has other object demarcations associated therewith.

15. The system of claim 13, in which a predefined object category comprises a preprinted character and which is operable to group preprinted characters into a word, thereby to group together the associated object demarcations.

16. The system of claim 15, which is operable to group words into a sentence.

17. The system of claim 13, in which a predefined object category comprises a character input field and which is operable to group character input fields into a text input field, thereby to group together the associated object demarcations.

18. The system of claim 14, in which a predefined object category comprises a checkmark field and which is operable to group together checkmark fields in the particular region, thereby to group together the associated object demarcations.

19. A machine-readable medium embodying a set of instructions which, when executed by a machine, causes the machine to:

analyze an image of a form to detect object demarcations on the form;

classify the object demarcations into one of a plurality of predefined object categories; and

process each object demarcation based on the object category into which it has been classified, thereby to create the form template automatically.