Abstract
Automatic recognition of handwritten alphanumeric characters is designed by making use of topological feature extraction and multi-level decision making. By properly specifying a set of easily detectable topological features, it is possible to convert automatically the handwritten characters into stylized forms and to classify them into primary categories. Each category contains one or several character pattern classes with similar topological configurations. Final recognition is accomplished by a secondary stage which performs local analysis on the characters in each primary category. The recognition system consists of two stages, global recognition followed by local recognition. Automatic character stylization results in pattern clustering which simplifies the classification tasks considerably, while allowing a high degree of generality in the acceptable writing format. Simulation of this scheme on a digital computer has shown only 2% misrecognition.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
W. T. Booth, G. M. Miller, and O. A. Schleich, “Design considerations for stylized font character readers,” inOptical Character Recognition, G. L. Fisher, D. K. Pollock, B. Raddack, and M. E. Stevens, eds. (Spartan Books, Washington, D.C., 1962).
J. Rabinow, “Developments in character recognition machines at Rabinow Engineering Company,” inOptical Character Recognition (1962).
F. N. Marzocco, “Computer recognition of handwritten first names,”IEEE Trans. Electronic Computers (1965).
M. Eden and M. Halle, “Characterization of cursive handwriting,”Proc. Fourth London Symposium on Information Theory, C. Cherry, ed. (Butterworth Scientific Publications, London, 1961).
R. M. Brown, “On-line computer recognition of handprinted characters,”IEEE Trans. Electronic Computers (1964).
E. C. Greanias, P. F. Meagher, R. J. Norman, and P. Essinger, “The recognition of handwritten numerals by contour analysis,”IBM J. Res. Develop. 7(1): (1963).
M. Eden and P. Mermelstein, “Mathematical models for the dynamics of handwriting generation,”Sixteenth Annual Conference on Engineering in Medicine and Biology, Vol. 5 (Conference Committee, Baltimore, 1963), pp. 12–13.
J. T. Tou, “On feature encoding in picture processing by computer,”Proceedings of the 7th Annual Allerton Conference (University of Illinois, Urbana, Illinois, 1969).
R. C. Gonzalez, “Pattern recognition via topological feature extraction,” Ph.D. dissertation, University of Florida, 1970.
R. S. Ledleyet al., “FIDAC: Film input to digital automatic computers and associated syntax-directed pattern recognition programming system,” inOptical and Electro-Optical Information Processing (M.I.T. Press, Cambridge, Mass., 1965).
J. T. Tou and R. C. Gonzalez, “A new approach to automatic recognition of handwritten characters,” Technical Report No. 70-101, Center for Informatics Research, University of Florida, November 1970.
Author information
Authors and Affiliations
Additional information
This work was supported in part by the Office of Naval Research and the National Science Foundation.
Rights and permissions
About this article
Cite this article
Tou, J.T., Gonzalez, R.C. Automatic recognition of handwritten characters via feature extraction and multi-level decision. International Journal of Computer and Information Sciences 1, 43–65 (1972). https://doi.org/10.1007/BF01108518
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF01108518