Handwritten Character Recognition via Radial Pixel Ratio Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current handwriting recognition systems face challenges in accurately recognizing cursive handwriting due to variations in size, orientation, and individual writing styles, and are limited in handling continuous and cursive writing, often relying on mapping strokes to recorded images rather than recognizing actual handwriting.
Innovation Solution
The method involves capturing handwritten characters as pixel images, partitioning them into line segments, and comparing pixel ratios to reference characters, with further segmentation and comparison if multiple matches are found, using techniques like identifying consecutive rows and columns of white pixels to dissect handwriting into lines, words, and characters, and reducing images to single-pixel width for recognition.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If existing handwriting recognition systems map writing strokes to recorded images, then character identification can be achieved, but the systems cannot accurately recognize cursive handwriting with variations in size, orientation and individual user styles
Solution Approach 1:
The patent divides a handwritten character into multiple radial segments extending from a central point. Each segment's pixel ratio (number of pixels in the segment divided by total pixels in the character) is calculated and compared to reference values. This segmentation approach allows the system to capture the essential structure of characters while being invariant to size, orientation, and stylistic variations, thereby resolving the contradiction between recognition accuracy and adaptability to different writing styles.
2Measurement precision
If the system partitions characters into multiple segments and compares pixel ratios, then recognition accuracy for varied writing styles improves, but the complexity of the recognition process increases
Solution Approach 1:
The patent transforms the complex problem of handwriting recognition by changing the parameters used for comparison. Instead of comparing entire character images or stroke sequences, the system calculates a simple pixel ratio for each radial segment and compares these ratios to pre-stored reference values. This parameter transformation simplifies the recognition process while maintaining high accuracy, effectively resolving the contradiction between precision and complexity.
3Productivity
If the system reduces character images to single-pixel width before comparison, then processing efficiency improves, but loss of character detail may occur
Solution Approach 1:
The patent extracts only the essential structural information needed for recognition by calculating pixel ratios in radial segments, rather than processing the entire character image or reducing it to a single-pixel width skeleton. This extraction approach maintains sufficient character detail for accurate recognition while significantly improving processing efficiency, resolving the contradiction between productivity and measurement precision.
Data Source
AI summary
A method, system and computer program product for recognizing cursive and non-cursive handwriting. The invention comprises capturing a handwritten character as an image of pixels, partition the image into a plurality of segments each having a pixel ratio of the number of pixels in the segment divided by the total number of pixels in the image, and compare the pixel ratio for each segment to a value range associated with a corresponding segment of a reference character. The handwritten character is recognized as the reference character if more than a predetermined number of the segments in the image have the pixel ratios within the respective value ranges of the reference character.