Character Recognition via Graphical Node and Edge Extraction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing character recognition techniques face challenges in identifying characters due to factors like magnification, rotation, varying lighting conditions, resolution limitations, perspective distortions, and poor image quality, especially when characters are not standardized.
Innovation Solution
A method and system that processes input images to extract nodes and edges, generating a graphical representation of characters, which is then compared to predetermined reference characters stored in a repository for recognition, using techniques such as Hough Transformation and edge detection to handle distortions and noise.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If standardized fonts are used for character recognition, then recognition accuracy is improved, but adaptability to non-standardized fonts deteriorates
Solution Approach 1:
The patent transforms characters into graphical representations by changing parameters such as node coordinates, edge connections, and structural relationships. This parameter transformation allows the system to recognize characters regardless of font style, size, or orientation, resolving the contradiction between recognition accuracy and adaptability to non-standardized fonts
Solution Approach 2:
The patent segments characters into fundamental components: nodes (vertices), edges (lines), and their spatial relationships. By breaking down characters into these basic graphical elements, the system can recognize characters based on their structural composition rather than relying on standardized font patterns, thereby achieving both accuracy and adaptability
2Reliability
If image processing techniques are used to handle distortions and noise, then recognition reliability is improved, but device complexity increases
Solution Approach 1:
The patent extracts essential graphical features (nodes and edges) from character images, separating the critical structural information from non-essential details such as font style, color, and background noise. This extraction process improves recognition reliability by focusing on invariant structural properties while avoiding the complexity of processing all image variations
Solution Approach 2:
The patent creates simplified graphical representations (copies) of characters that capture their essential structure without replicating all visual details. These graphical representations serve as robust templates for recognition, improving reliability while keeping the processing system simpler than working with full-resolution images
Data Source
AI summary
The present disclosure relates to a method and a system for recognizing characters. In one embodiment, the input image comprising one or more characters to be recognized is received and processed to extract one or more nodes and edges of each character in the input image. Using the extracted nodes and edges, a graphical representation and adjacency matrix of each character is generated and compared with a predetermined graphical representation and adjacency matrix to determine a match. Based on the comparison, a matching probability is determined based on which one or more characters in the input image is recognized and displayed as output. The proposed recognition method and system recognizes character with more accuracy and speed. Further, the present disclosure is simple, cost-effective and reduces the complexity involved in automatic recognition of characters.