This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Off-Line Cursive Script Word Recognition
January 1989 (vol. 11 no. 1)
pp. 68-83

Cursive script word recognition is the problem of transforming a word from the iconic form of cursive writing to its symbolic form. Several component processes of a recognition system for isolated offline cursive script words are described. A word image is transformed through a hierarchy of representation levels: points, contours, features, letters, and words. A unique feature representation is generated bottom-up from the image using statistical dependences between letters and features. Ratings for partially formed words are computed using a stack algorithm and a lexicon represented as a trie. Several novel techniques for low- and intermediate-level processing for cursive script are described, including heuristics for reference line finding, letter segmentation based on detecting local minima along the lower contour and areas with low vertical profiles, simultaneous encoding of contours and their topological relationships, extracting features, and finding shape-oriented events. Experiments demonstrating the performance of the system are also described.

[1] K. Badie and M. Shimura, "Machine recognition of roman cursive script," inProc. 6th Int. Conf. Pattern Recognition, Munich, West Germany, Oct. 1982, pp. 28-30.
[2] L. Bahl and F. Jelinek, "Decoding for channels with insertions, deletions and substitutions with applications to speech recognition,"IEEE Trans. Inform. Theory, vol. IT-21, Sept. 1975.
[3] M. Berthod and S. Ahyan, "On line cursive script recognition: A structural approach with learning," inProc. 5th Int. Conf. Pattern Recognition, Miami Beach, FL, Dec. 1980, pp. 723-725.
[4] H. Bouma, "Visual recognition of isolated lower case letter,"Vision Res., vol. 11, pp. 459-474, 1971.
[5] R. Bozinovic and S. N. Srihari, "A string correction algorithm for cursive script recognition,"IEEE Trans. Pattern Anal. Mach. Intell., vol. PAMI-4, pp. 655-663, Nov. 1982.
[6] R. Bozinovic and S. N. Srihari, "ROCS: A system for reading off-line cursive script," Dep. Comput. Sci., State Univ. New York at Buffalo, Buffalo, NY, TR 85- 13, Sept. 1985.
[7] M. Brown, "Cursive script recognition," Ph.D. dissertation, Univ. Michigan, Ann Arbor, MI, 1981.
[8] O. P. Buneman, "A grammar for the topological analysis of plane pictures,"Mach. Intell., vol. 4, pp. 383-393, 1969.
[9] D. J. Burr, "A normalizing transform for cursive script recognition," inProc. 6th Int. Conf. Pattern Recognition, Munich, West Germany, Oct. 1982, pp. 1027-1030.
[10] D. J. Burr, "Designing a handwriting reader,"IEEE Trans. Pattern Anal. Mach. Intell., vol. PAMI-5, pp. 554-559, Sept. 1983.
[11] A. Dutta, "An experimental procedure for handwritten character recognition,"IEEE Trans. Comput., vol. C-23, pp. 536-545, May 1974.
[12] L. D. Earnest, "Machine recognition of cursive script writing," inInformation Processing, C. M. Popplewell, Ed. Amsterdam, the Netherlands: North Holland, 1962.
[13] M. J. Eccles, P. S. McQueens, and D. Rosen, "Analysis of the digitized boundaries of planar objects,"Pattern Recognition, vol. 9, pp. 31-41, 1977.
[14] M. Eden, "On the formalization of handwriting," inProc. Symp. Appl. Math., vol. 12, 1961, pp. 83-88.
[15] R. Ehrich and K. Koehler, "Experiments in the contextual recognition of cursive script,"IEEE Trans. Comput., vol. C-24, pp. 182- 194, Feb. 1975.
[16] R. Farag, "Word-level recognition of cursive script,"IEEE Trans. Comput., vol. C-28, pp. 172-175, Feb. 1979.
[17] H. Freeman, "On digital computer classification of geometric line patterns," inProc. Nat. Elec. Conf., vol. 18, 1962, 312-324.
[18] L. S. Frishkopf and L. D. Harmon, "Machine reading of cursive script," inInformation Theory, C. Cherry, Ed. London, UK: Butterworth, 1961.
[19] R. N. Haber and L. R. Haber, "Visual components of the reading process,"Visible Lang., vol. XV, no. 2, pp. 147-181, 1981.
[20] K. Hayes, "Reading handwritten words using hierarchical relaxation," Univ. Maryland, College Park, MD, TR-783, 1979.
[21] J. J. Hull and S. N. Srihari, "A computational approach to word shape recognition: Hypothesis generation and testing," inProc. IEEE-CS Conf. Comput. Vision Pattern Recognition, June 1986, pp. 156-161.
[22] F. Jelinek, "A fast sequential decoding algorithm using a stack,"IBM J. Res. Develop., vol. 13, pp. 675-685, Nov. 1969.
[23] H. Kucera and W. N. Francis,Computational Analysis of Present Day American English. Providence, RI: Brown Univ. Press, 1967.
[24] P. Mermelstein and M. Eden, "Experiments on computer recognition of connected handwritten words,"Inform. Contr., vol. 7, pp. 255- 270, 1964.
[25] M. Minsky and S. Papert,Perceptrons. Cambridge, MA: M.I.T. Press, 1969.
[26] K. M. Sayre, "Machine recognition of handwritten words,"Pattern Recognition J., vol. 5, no. 3, pp. 213-228, Sept. 1973.
[27] S. N. Srihari, J. J. Hull, and R. Choudhari, "Integrating diverse knowledge sources in text recognition,"ACM Trans. Office Inform. Syst., vol. 1 no. 1, pp. 58-57, 1983.
[28] S. N. Srihari, Ed.,Computer Text Recognit. and Error Correction. Silver Spring, MD: IEEE Computer Society Press, 1984.
[29] S. N. Srihari and R. Bozinovic, "A multi-level perception approach to reading cursive script,"Artificial Intell., vol. 33, pp. 217-255, 1987.
[30] C. C. Tappert, "Cursive script recognition by elastic matching,"IBM J. Res. Develop., vol. 26, no. 6, pp. 765-771, Nov. 1982.
[31] C. C. Tappert, "Adaptive on-line handwriting recognition," inProc. 7th Int. Conf. Pattern Recognition, Montreal, P.Q., Canada, July-Aug. 1984, pp. 1004-1007.
[32] I. Taylor and M. M. Taylor,The Psychology of Reading. New York: Academic, 1983, pp. 183-193.
[33] G. Zachopoulos, "Slant estimation and correction for off-line cursive script," M.S. thesis, State Univ. New York at Buffalo, Buffalo, NY, 1984.

Index Terms:
character recognition; offline cursive script word recognition; character recognition; word image; feature representation; stack algorithm; lexicon; letter segmentation; local minima; character recognition; picture processing; statistical analysis
Citation:
R.M. Bozinovic, S.N. Srihari, "Off-Line Cursive Script Word Recognition," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 11, no. 1, pp. 68-83, Jan. 1989, doi:10.1109/34.23114
Usage of this product signifies your acceptance of the Terms of Use.