Digit Separator Line Removal in Document Image Processing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image processing technologies face challenges in efficiently removing digit separator lines from document images, which can lead to loss of characters representing monetary amounts and reduce the accuracy of optical character recognition (OCR) processes.
Innovation Solution
An image processing apparatus and method that utilize a scanner to read documents, detect digit separator lines separately from other ruled lines, and remove these lines from the image data. The apparatus includes a digit separator detection unit and a removal unit, which use a learned model to accurately identify and remove digit separator lines, even when they are printed in non-dropout colors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Object-affected harmful factors
If all ruled lines are removed from document images, then the visual clutter is reduced, but digit separator lines are incorrectly removed along with other ruled lines, causing loss of characters representing monetary amounts
Solution Approach 1:
The patent segments the removal process by first detecting specific digit separator lines that divide numerical values, then selectively removing only those lines while preserving other ruled lines. This segmentation allows differential treatment of different line types based on their functional characteristics.
Solution Approach 2:
The patent applies local quality by making the removal operation selective rather than uniform. Digit separator lines are identified by their specific characteristics (vertical orientation, position within numerical values) and removed only where appropriate, while other ruled lines retain their original appearance and function.
2Measurement precision
If digit separator lines are removed to improve OCR accuracy, then character recognition improves, but the detection process becomes more complex due to the need to distinguish digit separator lines from other ruled lines
Solution Approach 1:
The patent changes detection parameters by using multiple criteria (vertical orientation, position within numerical values, spacing patterns) to identify digit separator lines. This multi-parameter approach enables accurate distinction between digit separator lines and other ruled lines without requiring overly complex detection mechanisms.
3Productivity
If traditional ruled line removal methods are used, then the processing speed is maintained, but the accuracy of automatic processing in OCR is reduced due to character loss
Solution Approach 1:
The patent performs preliminary detection of digit separator lines before the removal operation. By identifying which lines are digit separators in advance using their specific characteristics, the system can then remove only those lines with high confidence, preventing character loss while maintaining processing efficiency.
Data Source
AI summary
An image processing apparatus includes a scanner to read a document and generate first image data of the document and circuitry. The circuitry detects a digit separator line, which is a vertical ruled line that divides a numerical value by one digit or three digits, in the first image data separately from another ruled line, and removes the digit separator line from the first image data.