Variable Skew Correction for Non-Linear Document Distortion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Document scanners often experience variable skew or non-linear distortion during scanning due to slippage between the document and the feed mechanism, especially with smooth or slippery surfaces, leading to curved or banana-shaped images.
Innovation Solution
A de-skew application that employs edge detection, linear line segmentation, partitioning, and deformation modeling to correct the skew by transforming scanned image data into a de-skewed output model, ensuring accurate representation of the document's edges and dimensions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a feed mechanism with rollers is used to feed the document past the photosensitive element, then the document can be scanned line-by-line, but variable skew or non-linear distortion occurs due to slippage between the document and feed mechanism
Solution Approach 1:
The system performs preliminary detection of document edges and determines skew parameters before the actual scanning process. By pre-calculating the skew correction parameters based on edge detection from a preliminary scan or document positioning, the system can compensate for anticipated slippage and maintain image linearity during high-speed scanning.
Solution Approach 2:
The system continuously monitors the scanned image for skew distortion and feeds this information back to adjust the scanning parameters or apply real-time correction. By detecting the actual skew that occurred during feeding and using this feedback to correct the image or adjust feed mechanism parameters, the system maintains both high scanning speed and image linearity.
2Stability of the object's composition
If the document has smooth or slippery surfaces (photo-quality paper, plastic), then the document can maintain its integrity, but slippage occurs between the document and feed mechanism causing variable skew
Solution Approach 1:
The system introduces an intermediary correction process between document feeding and image output. By detecting document edges and calculating skew parameters, the system applies a mathematical transformation (intermediary processing step) that compensates for the slippage effect, effectively mediating between the unavoidable mechanical slippage on smooth surfaces and the desired image accuracy.
Solution Approach 2:
Instead of relying solely on mechanical friction between rollers and smooth document surfaces to prevent slippage, the system substitutes mechanical grip with computational correction. By using edge detection and skew parameter calculation to apply digital correction to the scanned image, the system replaces the need for mechanical adhesion that would be required to prevent slippage on smooth surfaces.
3Loss of information
If embossed lettering or images are present on the document, then the document contains visual information, but friction increases causing uneven pressure and slippage
Solution Approach 1:
The system performs preliminary edge detection and skew parameter determination before completing the scanning process. By identifying the document boundaries and calculating anticipated skew from embossed features early in the process, the system can pre-adjust scanning parameters or prepare correction transformations to maintain image accuracy despite the friction-induced slippage from embossed lettering.
Data Source
AI summary
A variable skew correction system comprises a de-skew application executable to transform scanned image data of a document exhibiting a variable skew condition to an output model representing a de-skewed image of the document by transferring pixel data for each of a plurality of raster lines of the scanned image data to the output model, wherein a variable spacing between at least two adjacent raster lines of the scanned image data is modified in the output model to correct non-linear distortion of the scanned image data.