Golf Scorecard OCR Box Removal for Handwriting Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Handwritten characters partially or fully written on top of or inside rectilinear boxes pose challenges for accurate recognition by OCR software, leading to errors, especially when calculating series of handwritten numbers.
Innovation Solution
A scoring system that captures images of physical scorecards with handwritten characters, identifies and removes rectilinear boxes, and extracts handwritten characters as a continuous paragraph for accurate scoring.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If OCR software is used to recognize handwritten characters within rectilinear boxes, then character recognition can be performed, but recognition accuracy deteriorates when characters are written on top of or inside adjacent rectilinear boxes
Solution Approach 1:
The patent extracts and removes the rectilinear boxes from the image before performing OCR recognition. This separation eliminates the interference caused by characters written on or overlapping box boundaries, allowing the OCR software to accurately recognize characters without the distracting box structures present in the original image.
2Ease of operation
If rectilinear boxes are used to separate handwritten characters, then character separation can be achieved, but calculation accuracy of handwritten number series deteriorates due to OCR errors
Solution Approach 1:
The patent performs the box removal operation before OCR recognition and character extraction. By eliminating the rectilinear boxes in advance, the subsequent OCR process operates on a cleaner image where characters are not confounded by box boundaries, thereby ensuring both easy character separation and high calculation accuracy for number series.
3Productivity
If traditional OCR methods are used on characters within rectilinear boxes, then processing can be performed, but processing speed deteriorates due to repeated error correction
Solution Approach 1:
By removing rectilinear boxes before OCR processing, the patent eliminates the source of recognition errors that would otherwise require time-consuming correction cycles. This preprocessing step streamlines the entire workflow, allowing faster processing without the need for iterative error checking and correction.
Data Source
AI summary
A method to score a round of golf using a golf scoring system. The method includes capturing a photograph of a physical scorecard including handwritten text using a camera of a user device, wherein the physical scorecard includes handwritten characters disposed at least partially within rectilinear boxes. The method also includes accessing the photograph in an application of the user device. The method also includes identifying the rectilinear boxes by using a color contrast between the rectilinear boxes of the physical scorecard and a background color of the physical scorecard. The method also includes removing the rectilinear boxes. The method also includes after removing the rectilinear boxes, extracting at least the handwritten characters from the physical scorecard. The method also includes after extracting at least the handwritten characters, calculating a score of the round of golf using the extracted handwritten characters on the application.