Handwriting Recognition via Core Point Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for recognizing cursive handwriting are complex due to the challenge of segmenting connected characters, leading to errors in segmentation and recognition, and often require large statistical systems and extensive processing power.
Innovation Solution
A method that detects and recognizes handwritten patterns by selecting core points along the curves, determining features at these points, and comparing them to templates using a cumulative distance value calculation, which simplifies segmentation and recognition without needing neural networks or hidden markov models.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If cursive handwriting recognition is implemented to speed up data input, then productivity is improved, but device complexity increases due to the need for complicated statistical systems
Solution Approach 1:
The handwritten pattern is segmented into a sequence of points along curves, and core points are selected from this sequence to represent potential segmentation points between characters. This segmentation approach simplifies the recognition process by breaking down the complex cursive pattern into manageable discrete points that can be independently analyzed and matched against templates.
2Measurement precision
If neural networks and hidden markov models are used for cursive handwriting recognition, then measurement precision is improved, but use of energy and processing power increase significantly
Solution Approach 1:
Instead of using complex and computationally expensive neural networks or hidden Markov models, the invention employs simple template matching with pre-defined templates representing symbols or parts of symbols. This approach uses lightweight, easily computable distance values and cumulative distance calculations that require minimal processing power while maintaining acceptable recognition accuracy.
Solution Approach 2:
The invention changes the approach from probabilistic statistical modeling to geometric parameter-based comparison. By calculating distance values between corresponding points in the handwritten pattern and template symbols, and using cumulative distance values to determine recognition results, the system achieves recognition without requiring extensive computational resources.
3Measurement precision
If all points along the curves are used for recognition, then measurement precision is improved, but device complexity and processing time increase
Solution Approach 1:
Core points are extracted from the complete sequence of points along the handwritten curves. These core points represent critical locations such as potential segmentation points between characters and key features of the handwriting pattern. By focusing recognition analysis on these extracted core points rather than all points, the system reduces processing time and computational complexity while maintaining recognition accuracy.
Data Source
AI summary
A method for recognition of a handwritten pattern comprises selecting core points among a sequence of detected points of the handwritten pattern. The core points are selected for use in segmenting and recognizing the handwritten pattern. The method further comprises determining features of each core point, and comparing the handwritten pattern to templates. The comparing comprises stepwise analyzing the core points in sequence by matching the features of sequences of core points that either start with the first core point or the last core point of a previous sequence to said templates and calculating a distance value, and assigning a cumulative distance value to the last core point in the matched sequence of core points, whereby a smallest cumulative distance value is assigned to the last core point and corresponds to a sequence of matched templates which represent a possible recognition result of the handwritten pattern.