Graph Image Analysis via Type-Specific Probability Maps
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing techniques for analyzing graph images are limited to line graphs and require significant user input, making them less versatile and more burdensome for analyzing diverse graph types.
Innovation Solution
An information processing apparatus that acquires graph images, classifies them by type, generates probability maps, extracts components, and traces graphs, allowing for the analysis of diverse graph types with improved speed and accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If existing techniques are used to analyze graph images, then line graphs can be analyzed, but other graph types (bar graphs, pie charts) cannot be analyzed
Solution Approach 1:
The patent implements a universal graph analysis system that can handle multiple graph types (line graphs, bar graphs, pie charts, scatter plots, etc.) through a single integrated platform. The system uses graph type classification to identify the specific graph format and applies specialized analysis methods for each type, enabling multi-functional capability while maintaining high accuracy for each graph type through type-specific processing algorithms
2Ease of operation
If user specifies graph color and luminance amplitude to trace line graphs, then tracing can be performed, but user burden increases significantly
Solution Approach 1:
The system automatically performs graph tracing by detecting graph components and determining tracing parameters without requiring user input. The graph tracing unit autonomously identifies graph elements, determines appropriate tracing methods, and executes the tracing process, eliminating the need for users to manually specify colors, luminance amplitudes, or other parameters while maintaining high analysis speed through automated processing
3Ease of operation
If user sets X-axis, Y-axis, and scale to trace line graphs, then tracing can be performed, but user burden increases significantly
Solution Approach 1:
The system automatically detects and determines graph components including X-axis, Y-axis, scale, and other parameters without requiring user configuration. The graph component detection unit identifies these elements automatically, and the graph tracing unit uses the detected components to perform tracing, eliminating time-consuming manual parameter setting especially when analyzing large numbers of graphs
4Adaptability or versatility
If technique detects legend outside columns to trace line graph, then tracing can be performed, but graphs without legends cannot be analyzed
Solution Approach 1:
The system provides universal graph analysis capability that handles both graphs with legends and graphs without legends. The graph component detection unit can identify graphs based on their structural characteristics regardless of legend presence, and the graph tracing unit applies appropriate tracing methods for each graph type, ensuring reliable analysis for all graph formats including those without legends
Data Source
AI summary
To analyze images of more diverse graphs at higher speed and accuracy, disclosed herein is an information processing apparatus, comprising: a graph image acquisition unit configured to acquire a graph image; a graph classification unit configured to classify the graph image acquired by graph type; a probability map generation unit configured to generate, from the graph image, a probability map that is of a different type by the graph type; a component extraction unit configured to extract a plurality of components in the graph image based on the probability map generated by the probability map generation unit, and trace a graph with the plurality of components extracted; a value extraction unit configured to extract values of the components of the graph image extracted by the component extraction unit; and an output unit configured to output the values of the components extracted.