Answers are grounded in this paper and cite their sources.
The focus of this research is to develop general diagram recognition techniques based on quantitative experiments using machine learning to determine the most significant ink features and effective algorithms for use throughout the recognition process. This should improve on existing recognition success rates.
No takes yet. Share an insight, caveat, or question.
Blagojevic et al. (2008) studied this question.
Synapse has enriched 4 related papers. Consider them for comparative context: