Document Image Reliability Calculation for Targeted Output Routing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In form reading, there is a need to efficiently support the checking and correction of reading results, especially when multiple individuals are involved, to ensure accurate and efficient allocation of reading tasks.
Innovation Solution
An image-processing device and method that calculates the reliability of character recognition results based on feature amounts of specific items within document images and selects an appropriate output destination for the results, allowing for targeted checking and correction processes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If character recognition results are processed without reliability assessment, then the processing flow is simple, but the efficiency of checking and correction by multiple personnel is reduced
Solution Approach 1:
The system performs preliminary reliability calculation for each character recognition result before it enters the checking and correction phase. By pre-assessing reliability based on feature amounts (such as character clarity, position stability, and recognition confidence), the system prepares prioritized lists of results that need attention, enabling personnel to focus on low-reliability items first without adding complexity to the overall flow.
Solution Approach 2:
Different character recognition results are treated differently based on their individual reliability characteristics. The system applies local quality differentiation by categorizing results into high-reliability, medium-reliability, and low-reliability groups, allowing each group to follow different processing paths. This enables efficient allocation of checking and correction resources to specific local areas (individual results) based on their unique reliability profiles.
2Ease of operation
If all character recognition results are treated uniformly, then the system is simple to operate, but the allocation of checking and correction tasks becomes inefficient
Solution Approach 1:
The system performs self-service by automatically calculating and assigning reliability scores to each character recognition result based on intrinsic feature amounts. The reliability calculation unit autonomously analyzes features such as character clarity, position stability, and recognition confidence without requiring manual intervention. This self-assessment mechanism maintains ease of operation while significantly improving allocation efficiency by enabling the system to autonomously prioritize tasks for multiple personnel.
3Measurement precision
If reliability calculation is performed for all character strings, then the accuracy of reading results is improved, but the processing time increases
Solution Approach 1:
The system applies partial action by calculating reliability only for character strings that meet certain criteria or have specific feature characteristics. Rather than uniformly processing all character strings, the system focuses reliability calculation on those with ambiguous features, low confidence scores, or positional uncertainties. This selective approach maintains reading result accuracy for critical items while reducing overall processing time by avoiding unnecessary reliability calculations for clearly recognizable characters.
Data Source
AI summary
An image-processing device includes: a reliability calculation unit configured to calculate reliability of a character recognition result on a document image which is a character recognition target on the basis of a feature amount of a character string of a specific item included in the document image; and an output destination selection unit configured to select an output destination of the character recognition result in accordance with the reliability.