This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
A Knowledge-Based Approach for Script Recognition without Training
December 1995 (vol. 17 no. 12)
pp. 1233-1239

Abstract—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%.

[1] C.C. Tappert, C.Y. Suen, and T. Wakahara, “The State of the Art in On-Line Handwriting Recognition,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 12, no. 8, pp. 179-190, Aug. 1990.
[2] F.H. Farag,“Word-level recognition of cursive script,” IEEE Trans. Computers, vol. 28, no. 2, pp. 172-175, Feb. 1979.
[3] M. Parzeau and R. Plamondon,“Allograph adjacency constraints for cursive script recognition,” Proc. Third. Int’l Workshop Frontiers in Handwriting Recognition, pp.252-261,Buffalo, N.Y., 1993.
[4] T. Fujisaki,K. Nathan,W. Cho,, and H. Beigi,“On-line unconstrained handwriting recognition by a probabilistic method,” Proc. Third Int’l Workshop Frontiers in Handwriting Recognition, pp. 235-241,Buffalo, N.Y., 1993.
[5] G.M. Miller,“Real-time classification of handwritten script words,” Proc. IFIP Congress on Information Processing, 1971, pp. 218-223,Amsterdam, North Holland, 1972.
[6] P. Mermelstein, and M. Eden,“Experiments on computer recognition of connected handwritten words,” Information and Control, vol. 7, pp. 255-270, 1964.
[7] S. Bercu and G. Lorette,“On-line hand written word recognition: An approach based on hidden Markov models,” Proc. Third Int’l Workshop Frontiers in Handwriting Recognition, pp. 385-390,Buffalo, N.Y., 1993.
[8] L. Schomaker,“Using stroke-on character based self-organizing maps in the recognition of on-line connected cursive script,” Pattern Recognition, vol. 26, no. 3, pp. 443-450, 1993.
[9] C. Barriere and R. Plamondon,“Recognizing sequences of letters in mixed-script handwriting,” Proc. Conf. Vision Interface, pp. 83-91, 1992.
[10] E.G. Bellegarde,J.R. Bellegarde,D. Nahamov,, and K.S. Nathan,“A probabilistic frame-work for online handwriting recognition,” Proc. Third. Int’l Workshop Frontiers in Handwriting Recognition, pp. 225-233,Buffalo, N.Y., 1993.
[11] K.M. Sayre,“Machine recognition of handwritten words: A project report,” Pattern Recognition, vol. 5, pp. 213-228, Sept. 1973.
[12] M.Y. Chen and A. Kundu,“An alternative to variable duration HMM in hand written word recognition,” Proc. Third. Int’l Workshop Frontiers in Handwriting Recognition, pp. 82-91,Buffalo, N.Y., 1993.
[13] P.V.S. Rao,“Word-based recognition of cursive script,” NVA’90—IAPR Workshop Machine Vision Applications, pp. 441-444,Tokyo, 1990.
[14] V. Ramasubramanian and P.V.S. Rao,“Connected script synthesis by character concatenation—an overlap and weighted average formulation,” Computer Science Information, vol. 19, no. 1, pp. 1-10, 1988.
[15] P.V.S. Rao, and V. Ramasubramanian,“Connected script synthesis by character concatenation—a Bezier curve based formulation,” J. Inst. of Electronics and Telecommunications Eng., vol. 37, pp. 485-493, Sept.-Dec. 1991.
[16] P.V.S. Rao,“Shape vectors for on-line and off-line recognition of cursive script words,” ICDAR’91, First Int’l Conf. Document Analysis and Recognition, pp. 568-575,Saint Malo, France, 1991.
[17] P.V.S. Rao,“Shape vectors: An efficient parametric representation for the synthesis and recognition of hand script characters,” Sadhana 18, pp. 1-15, 1993.

Index Terms:
Character synthesis, cursive script, decoding, encoding, feature matrices, on-line recognition, script recognition, shape vectors, transfer function, transition segments.
Citation:
P.v.s. Rao, "A Knowledge-Based Approach for Script Recognition without Training," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 17, no. 12, pp. 1233-1239, Dec. 1995, doi:10.1109/34.476518
Usage of this product signifies your acceptance of the Terms of Use.