Table Line Tracing Using Cross Edge Vector Expansion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image processing methods face challenges in accurately recognizing the geometry of hand-drawn tables on writing boards due to irregularities such as faded lines, non-straight lines, and smudges, which result in low-quality input images that hinder the identification of pixels contributing to the intent of the table lines.
Innovation Solution
The method involves obtaining a mask of the stroke from an image, identifying cross edges, and expanding groups of cross edges using vectors to include adjacent and non-adjacent edges that do not intersect a reference line, thereby tracing the intent of the table line with high accuracy, even across discontinuities and gaps.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional image processing methods are used to recognize table lines, then processing speed is maintained, but measurement precision deteriorates due to faded lines, smudges, and discontinuities in hand-drawn tables
Solution Approach 1:
The patent segments the line tracing problem into distinct phases: identifying cross edges that intersect the reference line, grouping adjacent cross edges, and expanding groups using vector calculations. This segmentation allows each sub-problem to be solved with targeted algorithms, improving overall precision while managing complexity through modular processing steps.
Solution Approach 2:
The patent introduces a reference line dimension perpendicular to the stroke direction, enabling the identification of cross edges at multiple positions along the line. This dimensional approach allows the system to capture faded and discontinuous segments by looking at intersections from a new geometric perspective, thereby improving line identification accuracy.
2Reliability
If the image processing algorithm expands groups of cross edges using vector calculations, then line tracing accuracy improves across gaps and discontinuities, but computational time increases
Solution Approach 1:
The patent performs preliminary identification of cross edges that intersect the reference line before attempting to trace the complete line path. By pre-identifying these key intersection points and grouping adjacent cross edges, the system establishes a reliable foundation for subsequent vector-based expansion, reducing the computational burden during the tracing phase while maintaining robustness.
Solution Approach 2:
The patent uses vector calculations as an intermediary mechanism to bridge gaps between discontinuous cross edge groups. Instead of directly connecting disparate line segments, the vector expansion acts as a mediator that gradually extends groups based on directional information, improving reliability while controlling computational time through iterative expansion rather than exhaustive search.
3Measurement precision
If cross edges are identified based on intersections with a reference line, then line intent is captured accurately, but cross edges that do not intersect the reference line are missed
Solution Approach 1:
The patent merges two approaches: first identifying cross edges that intersect the reference line to capture line intent, then expanding groups to include adjacent cross edges that do not intersect the reference line. This combination ensures that both the directional information from intersections and the complete line geometry from adjacent edges are captured, preventing information loss while maintaining accurate intent recognition.
Solution Approach 2:
The patent applies different processing quality to different regions: cross edges intersecting the reference line are used for determining line direction and intent (high precision requirement), while adjacent non-intersecting cross edges are incorporated through vector expansion to complete the line geometry (moderate precision requirement). This local quality differentiation optimizes both accuracy and information capture.
Data Source
AI summary
A method for image processing includes obtaining a mask of a stroke from an image and identifying a plurality of cross edges for the stroke based on the mask and a reference line. The plurality of cross edges includes a group of adjacent cross edges that intersect the reference line. The method further includes (a) calculating a first vector based on positions of at least two of the cross edges in the group, (b) expanding the group, based on the first vector, to include cross edges adjacent to the group that do not intersect the reference line, (c) calculating a second vector based on positions of at least two of the cross edges in the expanded group, and (d) expanding the expanded group, based on the second vector, to include a second group of adjacent cross edges nearby the expanded group that do not intersect the reference line.