Handwritten Table Ruled Line Classification and Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Handwritten document processing systems face challenges in accurately extracting and shaping table ruled lines, especially when lengths are uneven or non-straight, and users often omit circumscribed ruled lines during handwriting inputs.
Innovation Solution
A handwritten document processing apparatus comprising an inputter, classifier, divider, and determiner that classifies stroke data, divides regions, and determines whether lines are small extension or circumscribed ruled lines, allowing for the estimation and display of correctly shaped tables.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If handwritten ruled lines are extracted directly from stroke data, then the processing speed is fast, but the accuracy of table shaping deteriorates due to uneven lengths and non-straight lines
Solution Approach 1:
The system performs preliminary classification of stroke data into ruled lines and non-ruled lines before detailed processing. This preliminary action separates the extraction of straight ruled lines (which can be processed quickly) from the handling of non-straight lines (which require additional processing), thus maintaining overall speed while improving accuracy.
Solution Approach 2:
The patent segments the processing into distinct stages: classification of stroke data, extraction of ruled lines, identification of small extension ruled lines, and separate handling of non-ruled lines. This segmentation allows each stage to be optimized independently, improving overall accuracy without significantly compromising processing speed.
2Device complexity
If all stroke data is processed as ruled lines, then the processing simplicity is high, but the reliability of table structure deteriorates due to inclusion of non-ruled lines
Solution Approach 1:
The system extracts and separates non-ruled lines from the stroke data using classification algorithms. By taking out these non-ruled lines and handling them separately, the system maintains processing simplicity for the majority of ruled lines while improving table structure reliability through dedicated handling of the extracted non-ruled line components.
3Manufacturing precision
If circumscribed ruled lines are required for complete table structure, then the table shaping completeness is improved, but the user input complexity increases as users must draw additional lines
Solution Approach 1:
The system performs self-service by automatically estimating and adding circumscribed ruled lines that are missing from user input. Instead of requiring users to manually draw all circumscribed lines, the system detects the table structure from the provided stroke data and automatically generates the missing circumscribed ruled lines, thus improving completeness without increasing user input complexity.
Solution Approach 2:
The system performs preliminary analysis of the stroke data to identify where circumscribed ruled lines are needed before final table rendering. This preliminary action allows the system to automatically supplement missing lines based on the detected table structure, ensuring completeness without requiring users to anticipate and draw all necessary lines in advance.
4Device complexity
If small extension ruled lines are not distinguished from regular ruled lines, then the processing simplicity is maintained, but the table shaping accuracy deteriorates
Solution Approach 1:
The system replaces manual mechanical distinction (where users would need to carefully draw different line types) with an automated computational system that uses algorithms to identify and classify small extension ruled lines. This substitution maintains processing simplicity by automating the distinction process while significantly improving table shaping accuracy through precise algorithmic identification.
Data Source
AI summary
According to one embodiment, a handwritten document processing apparatus includes an inputter, classifier, divider, and determiner. The inputter inputs stroke data. The classifier classifies the stroke data into data of a plurality of ruled lines and stroke data other than ruled lines. The divider divides a region including the plurality of ruled lines into first regions each corresponding to a cell bounded by four ruled lines and second regions each including at most three ruled lines. The determiner determines whether a ruled line in the second region is a first ruled line, to one end point of which a ruled line is not connected, or a second ruled line, to one end point of which a virtual circumscribed ruled line is connected.