Issue No. 12 - December (1995 vol. 17)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/34.476518
<p><it>Abstract</it>—The approach is based on an empirical parametric model for the writing hand system. The parameters are so chosen and quantized as to retain only broad shape information ignoring writer-dependent and other variability. Concatenation of character prototypes generates archetypal reference words for recognition; training is unnecessary. Recognition scores exceed 90%.</p>
Character synthesis, cursive script, decoding, encoding, feature matrices, on-line recognition, script recognition, shape vectors, transfer function, transition segments.
P. Rao, "A Knowledge-Based Approach for Script Recognition without Training," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 17, no. , pp. 1233-1239, 1995.