Paper Sheet Serial Number Recognition via GA Parameter Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The development of serial number recognition programs for paper sheets, such as paper currencies, is labor-intensive due to the need for individual customization for each recognition target, leading to increased man-hours.
Innovation Solution
A parameter determination apparatus and program that utilize a Genetic Algorithm (GA) to optimize parameter sets for serial number recognition, including binarization thresholds, dilation amounts, and distance thresholds, to improve recognition performance and reduce development time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If individual customization is performed for each recognition target, then recognition performance is improved, but development time and man-hours increase
Solution Approach 1:
The patent applies parameter changes by automatically optimizing recognition parameters (such as binarization thresholds, dilation amounts, and distance thresholds) for each recognition target using a Genetic Algorithm, rather than manually customizing the entire recognition program. This allows recognition performance to be tailored to each target while significantly reducing the development time and manual effort required.
2Measurement precision
If manual parameter optimization is performed, then recognition accuracy improves, but labor intensity increases
Solution Approach 1:
The system implements self-service by automatically determining optimal recognition parameters through a Genetic Algorithm that iteratively optimizes parameters based on recognition results. The apparatus performs self-optimization without requiring manual intervention for parameter tuning, thereby maintaining high recognition accuracy while eliminating the labor-intensive manual parameter optimization process.
Solution Approach 2:
The patent replaces the mechanical/manual process of parameter optimization with an automated computational system using Genetic Algorithm. This substitution eliminates the need for manual adjustment of recognition parameters while achieving optimal recognition accuracy through automated parameter determination.
3Reliability
If recognition programs are customized for each country, then recognition reliability improves, but device complexity increases
Solution Approach 1:
The patent applies universality by creating a single recognition program framework that can handle multiple recognition targets (different countries' paper currencies) through automatic parameter optimization. Instead of maintaining separate customized programs for each country, the system uses one universal program that automatically adapts to different targets by determining optimal parameters for each, thereby reducing device complexity while maintaining recognition reliability.
Data Source
AI summary
A serial number recognition parameter determination apparatus includes: a generation unit, an identification unit, and an evaluation index calculation unit. The generation unit generates a parameter set of a program, the program being used when a paper sheet handing apparatus identifies, from an image of a paper sheet, character present regions in which characters that form a serial number are present. The identification unit identifies, from an image of the paper sheet, the character present regions by using the parameter set that is generated by the generation unit. The evaluation index calculation unit calculates an evaluation index of the parameter set based on the character present regions that are identified by the identification unit.