Patterned Lines for Accurate ICR on Pre-Printed Forms
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing mark lifting technologies often distort user marks by removing significant portions near pre-printed form lines, leading to poor quality intelligent character recognition (ICR) results, as they require marks to be written inside a box and struggle with lines that intersect or cross the form boundaries.
Innovation Solution
Printing guiding lines and box boundaries as patterned lines that can be distinguished by mark lifting software, allowing for their removal without affecting user marks, thus enabling more accurate ICR by preserving user markings that intersect or cross these lines.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If solid lines are printed on pre-printed forms to guide user writing, then users can write naturally on lines, but mark lifting technology removes portions of user marks that cross these lines, distorting the marks and leading to poor ICR quality
Solution Approach 1:
The patent segments the continuous guiding lines into discrete patterned elements (such as dots, dashes, or geometric shapes) that are spaced apart. This segmentation allows the mark lifting software to identify and remove only the patterned guide elements while preserving continuous user marks that cross the guideline regions, thus resolving the contradiction between natural writing and ICR quality
Solution Approach 2:
The patent applies different visual characteristics to different parts of the form: patterned lines are used specifically in guideline regions where removal is needed, while other form elements maintain their traditional appearance. This localized application of patterned lines ensures that only the necessary guiding elements are removed during mark lifting, preserving user marks elsewhere and maintaining high ICR quality
2Productivity
If mark lifting technology removes pre-printed form lines from scans, then the form structure is eliminated for processing, but user marks near the lines are also removed, distorting the marks
Solution Approach 1:
By segmenting guiding lines into discrete patterned elements with specific spatial characteristics, the system enables the mark lifting software to selectively remove only these patterned elements while preserving user marks. The segmented patterned lines act as unique identifiers that can be recognized and removed without affecting the integrity of user-written content
Solution Approach 2:
The patent extracts the guiding line function from continuous solid lines and implements it through removable patterned lines. This extraction allows the guiding function to be separated from the permanent user mark data, enabling selective removal of only the guide elements during processing while preserving all user marks for ICR
3Extent of automation
If users are required to write inside a box to enable mark lifting, then the technology can process marks, but users must write in a floating manner that is difficult and unnatural
Solution Approach 1:
The patent segments the box boundary into patterned line elements that can be automatically removed by mark lifting software. This segmentation allows the box to serve its demarcation function during writing while enabling complete removal of the boundary after scanning, thus allowing users to write naturally within the box without the constraint of floating writing
4Manufacturing precision
If patterned lines are printed instead of solid lines, then user marks crossing the lines are preserved, but the lines must be distinguishable from user marks by machine while remaining indistinguishable to human eye
Solution Approach 1:
The patent employs variations in visual characteristics of the patterned lines (such as color, density, or geometric pattern) that create machine-detectable differences from user marks. These visual variations are subtle enough to appear as normal lines to human users but contain sufficient structural information for automated recognition and selective removal by software algorithms
Data Source
AI summary
Methods, devices, and systems replace solid lines of user-fillable areas of a print job with patterned lines and then print the print job with the patterned lines to print user-fillable pre-printed forms, using a printing device. These methods, devices, and systems also scan at least one of the user-fillable pre-printed forms having user markings to produce a scan, using an optical scanner. Further, such methods, devices, and systems produce an altered scan by removing only the patterned lines from the scan to leave the user markings in the altered scan using the image processor. Then, these methods, devices, and systems can identify user-supplied characters by performing automated character recognition on the user markings in the altered scan using the image processor and output such user-supplied characters from the image processor.