Virtual Form Generation for Distorted Document Alignment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current automated systems face challenges in accurately aligning and identifying scanned paper forms with their corresponding blank versions, especially when forms undergo distortions due to printing, photocopying, or faxing, leading to misalignment and noise in digital representations.
Innovation Solution
The method involves creating a virtual filled-in form by mapping the content of a filled-in form onto a blank form using statistical techniques, correcting for distortions, and generating a virtual form that aligns with the blank form, allowing for the extraction of annotations without misalignment concerns, and storing only the blank form for efficient storage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If forms are scanned and stored as digital images, then forms can be processed automatically, but alignment accuracy deteriorates due to distortions from printing, photocopying, or faxing
Solution Approach 1:
The patent creates a virtual filled-in form by copying and mapping content from the scanned filled-in form onto a template blank form. This virtual form is then used for processing and storage, eliminating the need to store the original scanned form with its distortions while maintaining alignment accuracy through the template-based approach.
Solution Approach 2:
The template blank form serves as an intermediary that mediates between the scanned filled-in form and the processing system. By mapping the scanned form's content onto the template, the system corrects distortions and achieves accurate alignment without requiring the scanned form itself to be perfectly aligned.
2Loss of information
If filled-in forms are stored as digital images, then form information is preserved, but storage efficiency deteriorates due to redundant storage of blank form content
Solution Approach 1:
The patent extracts only the necessary information (annotations and filled-in content) from the scanned filled-in form and maps it onto the template blank form. The resulting virtual form stores only the essential data, eliminating redundant storage of blank form content while preserving all necessary form information.
Solution Approach 2:
The template blank form serves multiple functions: it acts as a storage container for form data, provides a reference for alignment, and enables the creation of virtual filled-in forms. This multi-functionality reduces the need to store multiple versions of forms, improving storage efficiency.
3Adaptability or versatility
If forms undergo printing, photocopying, or faxing, then forms can be distributed and processed, but noise and distortions are introduced into the digital representation
Solution Approach 1:
The patent performs preliminary action by creating the virtual filled-in form through mapping onto the template before the form is used for processing or storage. This preliminary creation process corrects distortions and noise introduced during distribution, ensuring high accuracy in the final digital representation.
Solution Approach 2:
The patent creates a clean copy of the form by mapping the scanned form's content onto a perfect template blank form. This copying process eliminates noise and distortions from the original scanned form while preserving all essential information, resulting in a high-accuracy digital representation.
Data Source
AI summary
Methods and apparatus for comparing blank forms represented in a digital format to digitized filled-in forms are described. Different errors are attributed different weights when attempting to correlate regions of blank and filled-in forms. Foreground pixels in the blank form which are not found in a corresponding portion of a filled-in form are attributed greater error significance than foreground pixels, e.g., pixels which may correspond to added text, found in the filled-in form which correspond to a background pixel value in the blank form. A virtual filled-in form including content, e.g., pixel values, from the filled-in form is generated from the content of the filled-in form and pixel value location mapping information determined from comparing the blank and filled-in forms. Various analysis is performed on a block basis, but in some embodiments the final pixel mapping to the virtual form is performed on a pixel by pixel rather than a block basis.