Image Processing System for Identifying Table Captions in Electronic Forms
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Identifying row and column captions in tables of electronic forms is challenging, especially when processing scanned documents, as existing technologies struggle to accurately position information within electronic databases.
Innovation Solution
An image processing system that uses a processor and computer-readable storage medium to identify boxes in a scanned document, create a data structure for fillable forms, and apply algorithms to determine adjacent boxes, row, and column captions by traversing adjacency lists, thereby correctly associating empty boxes with their respective captions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional image processing methods are used to identify tables in scanned documents, then the processing can be completed with simple algorithms, but the accuracy of identifying row and column captions is poor
Solution Approach 1:
The patent segments the table identification process into distinct phases: detecting table boundaries, identifying empty boxes, traversing adjacency lists to locate captions, and differentiating between row and column captions. This segmentation allows each sub-task to be handled by specialized algorithms, improving overall accuracy while managing complexity through modular processing
Solution Approach 2:
The patent introduces an adjacency list data structure as an intermediary between the detected table boxes and the caption identification process. This intermediary organizes spatial relationships between boxes, enabling systematic traversal to locate captions without requiring complex direct analysis of box relationships
2Productivity
If manual methods are used to identify and position table captions, then the accuracy of caption positioning is high, but the processing time and productivity are low
Solution Approach 1:
The system performs self-service by automatically identifying captions through algorithmic traversal of adjacency lists. The process autonomously determines which boxes contain row captions versus column captions based on their positional relationships, eliminating manual intervention while maintaining accuracy through systematic logic
Solution Approach 2:
The patent performs preliminary actions by first detecting all table boxes and constructing the adjacency list structure before proceeding to caption identification. This preliminary organization of spatial relationships enables faster subsequent processing compared to methods that attempt to identify captions without pre-established structural information
3Adaptability or versatility
If simple box detection is performed without creating adjacency relationships, then the processing complexity is low, but the ability to identify row and column captions is insufficient
Solution Approach 1:
The patent segments the table data into individual box entities with explicit adjacency relationships. By representing the table as a collection of boxes with defined connections (adjacency list), the system gains the adaptability to traverse and analyze caption positions while managing complexity through structured data organization
Solution Approach 2:
The patent adds a relational dimension to the box detection by creating adjacency lists that capture spatial relationships between boxes. This transforms the problem from simple box detection to a two-layer structure: geometric box positions plus topological adjacency relationships, enabling sophisticated caption identification without overwhelming complexity
Data Source
AI summary
An image processing system for identifying table captions may include a processor and a non-transitory computer-readable storage medium comprising one or more instructions configured to cause the processor to perform image processing of a scanned document to identify boxes of an electronic fillable form that corresponds to the scanned document. The system creates and stores a data structure that includes a box list. The system searches the box list to identify an empty box, uses an adjacency list determine whether the empty box has adjacent boxes, and in response to determining that the empty box has one or more adjacent boxes, creates a table box list that includes the empty box and one or more other boxes from the table to which the empty box belongs. The system uses the adjacency list to identify a row caption and a column caption associated with the empty box.