Form Identification via Line Position Model Extraction

Solution Overview

Problem

Existing automated processes for identifying forms are time-consuming and require significant processing power, especially when dealing with frame-based documents, as they often rely on image registration and storage of large files.

Innovation Solution

A system that normalizes document images by identifying the relative positions of vertical and horizontal lines, generating a model, and comparing these positions to existing models to identify matching forms, using preprocessing, layout extraction, model generation, and matching algorithms to efficiently classify forms.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If image registration is used to compare actual images from two forms, then form identification accuracy is improved, but processing time and storage requirements increase significantly

Engineering Contradiction:

Improveform identification accuracyVSAvoidprocessing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent extracts only the essential structural features (vertical and horizontal line positions) from complete form images, creating a simplified model that retains identification accuracy while eliminating unnecessary image data. This extraction approach compares line position arrays rather than full images, dramatically reducing processing time and storage requirements.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The patent creates simplified copies of form structures by generating models consisting of arrays representing vertical and horizontal line positions. These model arrays serve as compressed representations that enable rapid comparison without requiring the original full-resolution images, thus improving processing efficiency while maintaining identification capability.

Inventive Principle:

Principle #26Copying

2Measurement precision

If image registration is used to compare actual images from two forms, then form identification accuracy is improved, but processing power requirements increase significantly

Engineering Contradiction:

Improveform identification accuracyVSAvoidprocessing power

Core Design Contradiction:

Measurement precisionVSPower

Solution Approach 1:

The patent extracts only the essential structural features (vertical and horizontal line positions) from complete form images, creating a simplified model that retains identification accuracy while eliminating unnecessary image data. This extraction approach compares line position arrays rather than full images, dramatically reducing processing time and storage requirements.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The patent creates simplified copies of form structures by generating models consisting of arrays representing vertical and horizontal line positions. These model arrays serve as compressed representations that enable rapid comparison without requiring the original full-resolution images, thus improving processing efficiency while maintaining identification capability.

Inventive Principle:

Principle #26Copying

3Measurement precision

If complete form images are stored for comparison, then identification accuracy is improved, but storage requirements increase significantly

Engineering Contradiction:

Improveidentification accuracyVSAvoidstorage space

Core Design Contradiction:

Measurement precisionVSQuantity of substance

Solution Approach 1:

The patent extracts only the essential structural features (vertical and horizontal line positions) from complete form images, creating a simplified model that retains identification accuracy while eliminating unnecessary image data. This extraction approach compares line position arrays rather than full images, dramatically reducing processing time and storage requirements.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The patent creates simplified copies of form structures by generating models consisting of arrays representing vertical and horizontal line positions. These model arrays serve as compressed representations that enable rapid comparison without requiring the original full-resolution images, thus improving processing efficiency while maintaining identification capability.

Inventive Principle:

Principle #26Copying

Data Source

PatentUS8559729B2Automatic forms identification systems and methods

Publication Date: 2013.10.15 HYLAND SWITZERLAND SARL

AI summary

Systems and methods automatically generate a model of a form or other document and identify the form or other document. In one aspect, a system and method normalize an image of a document and identify the relative positions of vertical and horizontal lines in the normalized image. The relative positions of vertical and horizontal lines of the normalized image are the model of the document image. The model may be stored in a record, such as an array. The system and method compare the relative positions of vertical and horizontal lines of the model to the relative positions of vertical and horizontal lines of other models to identify a matching model.