A fuzzy substroke extractor for handwritten Chinese characters

摘要

This paper incorporates fuzzy technique into handwritten Chinese character substroke extraction. By computing a fuzzy score for every possible substroke, feature loss is reduced without imposing unnecessary restrictions on the writing style. Our extractor is as good as existing crisp substroke extractors in unambiguous situations, and it outperforms them in ambiguous cases in terms of the number of desirable substrokes extracted. Comparing with the “explore-every-possibility” approach based on crisp decision, we arrive at the correct feature set in a smaller number of iterations. The extractor's performance could also be tuned via a number of system parameters.