Stroke-Based Handwriting Recognition for Script Independence
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current online handwritten character recognition systems are inadequate for script-independent recognition of sub-word units and words, particularly for languages like Germanic, Slavic, Romanic, and Indic languages, due to limitations in feature extraction, spatio-temporal analysis, and user-friendliness, especially for English non-literate populations.
Innovation Solution
A method and system that recognizes individual strokes prior to sub-word unit and word recognition, utilizing a spatio-temporal analysis module, stroke extraction and separation, pre-processing, feature extraction with Fuzzy Directional Features, and error analysis to enhance recognition accuracy and adaptability across different scripts.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If online handwritten character recognition is implemented for script-independent languages, then communication accessibility is improved, but recognition accuracy deteriorates due to large sub-word unit sets and varying writing styles
Solution Approach 1:
The patent segments the recognition process into three hierarchical levels: stroke recognition (basic building blocks), sub-word unit recognition (combining strokes), and word recognition (combining sub-word units). This segmentation allows the system to handle script-independent languages by breaking down complex recognition tasks into manageable stages, improving accuracy despite large sub-word unit sets and writing style variations.
2Measurement precision
If feature extraction and spatio-temporal analysis are performed for stroke recognition, then recognition accuracy is improved, but system complexity increases
Solution Approach 1:
The patent performs preliminary stroke recognition and extraction before proceeding to sub-word unit and word recognition. By pre-processing and identifying individual strokes with spatio-temporal analysis, the system establishes an accurate foundation for subsequent recognition stages, improving overall accuracy while managing complexity through staged processing.
3Device complexity
If conventional keyboards are used for non-English languages, then device simplicity is maintained, but ease of operation deteriorates due to transliteration requirements
Solution Approach 1:
The patent replaces the mechanical keyboard input system with an online handwritten recognition system that captures pen strokes dynamically. This substitution eliminates the need for transliteration and knowledge of English alphabets, allowing users to write directly in their native scripts while maintaining device simplicity through software-based recognition.
Data Source
AI summary
The present invention relates to a method and system for online script independent recognition of handwritten sub-word unit and words. More particularly the present invention relates to a system and method which enables online recognition of script independent sub-word unit and words by recognizing the written individual strokes prior to recognition of sub-word unit and words. The present invention provides an easy and natural to use method for handwritten sub-word unit and word recognition, wherein the application can be deployed on the existing communication means.