Automatic Segmentation Parameter Selection for Optical Character Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Setting up optical character recognition (OCR) parameters for machine vision systems is challenging, especially for new users, as it often requires technical expertise to adjust segmentation parameters, which can be difficult when default settings fail, especially with new parts or printing/labels introduced.
Innovation Solution
A computer-implemented method that automatically generates and selects segmentation parameters for OCR, allowing users to interactively set up OCR tools with minimal input, includes user-selectable options for indicating correct or incorrect segmentations, and automatically tunes parameters based on statistical properties of good characters, ensuring compliance with criteria like ASCII uniformity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If default segmentation parameters are used, then setup is easy, but recognition accuracy deteriorates when default parameters don't work
Solution Approach 1:
The system performs self-adjustment of segmentation parameters by automatically analyzing image characteristics and tuning parameters without requiring user expertise. The OCR system monitors its own performance and autonomously modifies parameters to maintain high recognition accuracy across different text scenarios.
Solution Approach 2:
The system dynamically changes segmentation parameters based on image analysis. By detecting text characteristics in the input image, the system automatically adjusts parameters such as segmentation thresholds, character boundaries, and recognition sensitivity to optimize accuracy for the specific text type and quality.
2Reliability
If manual parameter adjustment is enabled, then recognition accuracy can be improved, but user skill requirement increases
Solution Approach 1:
The system performs self-adjustment of segmentation parameters by automatically analyzing image characteristics and tuning parameters without requiring user expertise. The OCR system monitors its own performance and autonomously modifies parameters to maintain high recognition accuracy across different text scenarios.
Solution Approach 2:
The system uses feedback from recognition results to automatically adjust parameters. By monitoring recognition accuracy and performance metrics, the system feeds this information back into the parameter adjustment process, continuously optimizing segmentation settings based on actual performance rather than requiring manual user intervention.
3Adaptability or versatility
If more segmentation parameters are provided, then recognition flexibility increases, but system complexity increases
Solution Approach 1:
The system dynamically determines which parameters to adjust based on the specific text characteristics and recognition needs. Rather than presenting all possible parameters statically, the system activates and adjusts only the relevant parameters for the current text type, quality, and context, making the system adaptable without overwhelming the user with complexity.
Data Source
AI summary
A computer-implemented method for selecting at least one segmentation parameter for optical character recognition is provided. The method can include receiving an image having a character string that includes one or more characters. The method can also include receiving a character string identifying each of the one or more characters. The method can also include automatically generating at least one segmentation parameter. The method can also include performing segmentation on the image having the character string using the at least one segmentation parameter. The method can also include determining if a resultant segmentation satisfies one or more criteria and if the resultant segmentation satisfies the one or more criteria, selecting the at least one segmentation parameter.