Methods and devices for form-independent registration of filled-out content

• US 9,374,501 B2
• Filed: 03/04/2014
• Issued: 06/21/2016
• Est. Priority Date: 03/04/2014
• Status: Active Grant

• Current Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Original Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Inventors: Campanelli, Michael R, Wshah, Safwan R
• Primary Examiner(s): Allison, Andrae S
• Application Number:
  US14/196,108
• Publication Number:
  US 20150256712A1
• Time in Patent Office: 840 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 18/00 Pattern recognition
• CPC Class Codes: G06V 30/412 Layout analysis of documents structured with printed lines or input boxes, e.g. business forms or tables
• CPC Class Codes: G06V 30/414 Extracting the geometrical structure, e.g. layout tree; Block segmentation, e.g. bounding boxes for graphics or text
• CPC Class Codes: H04N 1/0432 Varying the magnification of a single lens group
• CPC Class Codes: H04N 1/4177 encoding document change data, e.g. form drop out data
• CPC Class Codes: H04N 2201/0081 Image reader H04N2201/0091 - H04N2201/0094 take precedence

Abstract

A device for registration of content in a filled-out application form is disclosed. The device is configured for scanning at least one portion of the filled-out application form. The device is configured for extracting filled-out content from the scanned form. The geometrical features of the master form are retrieved. The master form includes one or more anchor fields. Each anchor field has one or more anchor zones and at least one anchor segment. At least one anchor segment has global adjustment parameters and geometrical features. The extracted filled-out content is related to the retrieved geometrical features of a master form to create a new geometrical representation of the extracted filled-out content of the scanned application form. The new representation of the filled-out content based on the global adjustment parameters for the at least one anchor segment is globally adjusted. The globally adjusted filled-out content based on the geometrical features for the anchor segments is locally adjusted.

Claims

1. A document content registration system comprising:

an imaging unit for scanning at least one portion of a form containing content comprising a plurality of fields and corresponding field values which have been filled into said fields, and generating a scanned form;

an extraction module for receiving said scanned form from said imaging unit and for extracting only content from said scanned form with field values that have been filled-in, said extraction module dropping out color and background from said scanned form, and generating an extracted image;

a template retrieval module for retrieving geometrical features of a master form comprising, at least in part, predetermined anchor fields each corresponding to at least one anchor zone and at least one-anchor segment, said anchor fields and anchor zones having global adjustment parameters comprising scale, rotation and shift and geometrical features which define dimensions of said anchor zones, said master form being a universal form which can be referenced for a plurality of different forms;

a comparison module receiving said extracted image from said extraction module and said geometrical features of said master form from said template retrieval module, and comparing geometrical features of said anchor segments of said scanned form with corresponding anchor fields in said master form to create a new geometrical representation of said extracted content of said scanned form;

a global registration module for globally adjusting said new geometrical representation of said content based on global adjustment parameters of said anchor fields and anchor zones, said global registration module producing a globally adjusted form; and

a local registration module for performing location registration on said globally adjusted form, said registration comprising iteratively adjusting of each of said globally adjusted segments until all segments have been locally adjusted, said adjustment being based on said geometrical features for said content.

2. The document content registration system of claim 1, further comprising a receiving module for receiving said scanned image from said scanning unit and for providing said received scanned image to said extraction module.

3. The document content registration system of claim 1, wherein said template retrieval module is a memory module.

4. The document content registration system of claim 1, wherein said template retrieval module sends both said extracted form and said retrieved master form to said comparison module.

5. A method for document content registration comprising:

scanning, by an imaging unit, at least one portion of a form containing content comprising a plurality of fields and corresponding field values which have been filled into said fields, to generate a scanned form;

receiving, by an extraction module, said scanned form from said imaging unit and extracting content from said scanned form, said extraction module dropping out color and background from said scanned form, and generating an extracted image containing only content with field values that have been filled-in;

receiving, by an extraction module, said scanned form and extracting content from said scanned form, said extraction module dropping out color and background information from said scanned form, and generating an extracted image containing only content with field values that have been filled-in, said extracted image to undergo content registration;

retrieving, by a template retrieval module, geometrical features of a master form comprising, at least in part, predetermined anchor fields each corresponding to at least one anchor zone and at least one anchor segment, said anchor fields and anchor zones having global adjustment parameters comprising scale, rotation and shift and gometrical features which define dimensions of said anchor zones, said master form being a universal form which can be referenced for a plurality of different forms;

receiving, by a comparison module, said extracted image from said extraction module and said geometrical features of said master form from said template retrieval module, and comparing geometrical features of said anchor segments of said scanned form with corresponding anchor fields in said master form to create a new geometrical representation of said extracted content of said scanned form;

globally adjusting, by a global registration module, said new geometrical representation of said content based on global adjustment parameters of said anchor fields and anchor zones, said global registration module producing a globally adjusted form; and

iteratively adjusting, by a local registration module, each of said globally adjusted segments until all segments have been locally adjusted, said adjustment being based on said geometrical features for said content.