Image Processing Device for Automated OCR Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The burden on operators checking OCR process results is high, as existing methods do not efficiently match data acquired through OCR with pre-acquired data, leading to increased effort in error detection and correction.
Innovation Solution
An image processing device and method that selects feature quantities from document images, performs character recognition, and determines matching character strings, reducing operator burden by using pre-recorded and input data for matching and machine learning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If character recognition is performed on document images using conventional OCR methods, then character strings can be extracted, but the accuracy is insufficient and requires extensive manual checking and correction by operators
Solution Approach 1:
The system performs preliminary actions by acquiring determination results from multiple determination devices before final output. These determination results are obtained in advance through parallel processing, allowing the system to prepare corrected character strings before they are needed, thereby reducing operator burden and improving accuracy without requiring manual intervention during the main processing flow
Solution Approach 2:
The system introduces determination devices as intermediaries between the OCR processing and final output. These intermediaries evaluate and correct character recognition results by comparing them against expected patterns and multiple alternative interpretations, acting as a mediator that filters out errors before results reach the operator or downstream systems
2Measurement precision
If multiple determination devices are used to evaluate character strings, then accuracy improves, but processing time and system complexity increase
Solution Approach 1:
The system implements periodic action by having multiple determination devices operate in parallel cycles, each evaluating character strings independently at the same time. This periodic parallel evaluation allows the system to achieve high accuracy through multiple perspectives without sequential processing delays, as all determination devices work simultaneously rather than in sequence
Solution Approach 2:
The evaluation process is segmented into multiple independent determination devices, each handling specific aspects of character string evaluation. This segmentation allows the system to divide the complex evaluation task into manageable parallel components that can be processed simultaneously, reducing overall processing time while maintaining comprehensive evaluation accuracy
3Measurement precision
If character recognition results are manually checked and corrected, then accuracy improves, but productivity decreases due to increased operator effort
Solution Approach 1:
The system implements self-service by enabling automatic correction of character recognition errors through determination devices that independently evaluate and correct results without human intervention. The system serves itself by using its own resources (determination devices, comparison algorithms) to identify and correct errors, eliminating the need for manual operator involvement in the correction process
Solution Approach 2:
The system establishes a feedback mechanism where determination results are fed back into the processing flow to automatically correct errors. The comparison between OCR results and determination results creates a closed-loop feedback system that continuously refines accuracy by using the determination outcomes to adjust and correct the character strings, maintaining high accuracy while preserving processing throughput
Data Source
AI summary
An image processing device including: a first feature quantity selecting unit configured to select a first feature quantity of a document image that is a character recognition target among first feature quantities that are recoded in advance and represent features of character strings of an item; a character recognition processing unit configured to perform a character recognition process for the document image; a character string selecting unit configured to select a character string of a specific item corresponding to the first feature quantity among the character strings acquired as a result of the character recognition process; and a determination result acquiring unit configured to acquire a determination result indicating whether or not a character string that has been input in advance matches the character string of the specific item in a case in which the character string selecting unit has not selected any one of the character strings.