The Stroke Correspondence Problem, Revisited
This work addresses the stroke correspondence problem for Japanese character recognition, but it is incremental as it builds on prior methods.
The paper revisits the stroke correspondence problem by optimizing an existing algorithm through preprocessing, extending distance measures for Japanese characters, and simplifying stroke linking, with implementations in open-source tools.
We revisit the stroke correspondence problem [13,14]. We optimize this algorithm by 1) evaluating suitable preprocessing (normalization) methods 2) extending the algorithm with an additional distance measure to handle Hiragana, Katakana and Kanji characters with a low number of strokes and c) simplify the stroke linking algorithms. Our contributions are implemented in the free, open-source library ctegaki and in the demo-tools jTegaki and Kanjicanvas.