Issue No. 12 - December (1997 vol. 19)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/34.643898
<p><b>Abstract</b>—We present a distortion-tolerant on-line cursive Kanji character recognition method that absorbs the stroke-based handwriting distortion expressible by uniform affine transformation. Experiments are made using two kinds of test data in the square style and in the cursive style for 2,980 Kanji character categories; recognition rates of 98.4 percent and 96.0 percent are obtained.</p>
On-line Kanji character recognition, one-to-one stroke correspondence, affine transformation, least-squares criterion, deformation model, distortion-tolerant shape matching.
K. Odaka and T. Wakahara, "On-Line Cursive Kanji Character Recognition Using Stroke-Based Affine Transformation," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 19, no. , pp. 1381-1385, 1997.