OCR System Font Matching for Form Recognition Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional OCR systems face challenges in maintaining recognition accuracy when font types differ, increase the burden of correction work due to unreliable processing, and struggle to accurately acquire character strings without specific information marks.
Innovation Solution
The OCR system includes an OCR information management section that associates issuer identification with font types and processing reliability, and a performance section that performs OCR processing using the associated font type, while also using specific marks to indicate reliability and extract character strings within a specified distance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional OCR processing is performed without font matching, then processing speed is maintained, but character recognition accuracy decreases when font types differ
Solution Approach 1:
The system performs preliminary font type identification on the input text before OCR processing. By detecting the font type in advance and storing it in memory, the OCR processing section can subsequently match the processing font to the text font, thereby improving character recognition accuracy without significantly increasing overall processing complexity
Solution Approach 2:
The system changes the font type parameter used in OCR processing based on the detected text font type. By dynamically adjusting the processing font parameter to match the text font, the system optimizes recognition accuracy for different font types while maintaining efficient processing
2Ease of operation
If OCR processing is performed without reliability indication, then processing simplicity is maintained, but user burden increases due to inability to perceive processing reliability
Solution Approach 1:
The system provides feedback to the user by displaying reliability marks next to recognized text. The reliability mark is determined based on the match between the text font type and the OCR processing font type, allowing users to quickly identify and prioritize correction work without increasing system complexity
Solution Approach 2:
The system uses visual indicators (reliability marks) to convey processing quality information to users. By displaying different marks for high and low reliability text, the system enables users to efficiently assess and manage correction priorities
3Measurement precision
If specific information marks are required on all characters, then acquisition precision is improved, but ease of operation decreases when marks are missing on some characters
Solution Approach 1:
The system applies partial marking, placing specific information marks only on certain characters within a recognized text range rather than requiring marks on all characters. This approach maintains acquisition precision for marked characters while reducing the operational burden of comprehensive marking
Solution Approach 2:
The system performs preliminary text range recognition using OCR before applying specific information marks. By first identifying the text range and then selectively marking characters within that range, the system improves both acquisition accuracy and operational efficiency
Data Source
AI summary
An OCR system which acquires character data from a form (50) through OCR processing is characterized by: managing an OCR information table (34e) in which an issuer name of an issuer on the form (50) is associated with a font name of a font used in the OCR processing; and, when the OCR processing is performed on an issuer-recorded content reading target area in the form (50), performing the OCR processing (S156) in the font indicated by the font name associated in the OCR information table with the issuer name of the issuer of the form (50).