ABSTRACT
This paper describes a commercial hardware/software system which reads handprinted documents. The system recognizes a full upper case alphabet, all ten digits, and several special characters, intermixed, with minimal constraints imposed on the style of printing. The recognition algorithm, which incorporates a large number of heuristic methods, is described. On a test of over sixty thousand previously unseen characters produced by untrained clerks, fewer than six percent of the characters were “rejected” as unrecognizable, and only a few tenths of a percent were misrecognized.
- 1.A. K. Griffith, "The GRAFIX I Image Processing System" AFIPS Proc. 1974 National Computer Conference, May 6-10, 1974, Chicago, pp. 267-272.Google Scholar
- 2.S. B. Gray, "Technical Description of The GRAFIX I Image Processing System", document 90340, Information International Inc, Los Angeles, Calif. 1971.Google Scholar
- 3.S. B. Gray, "The Binary Image Processor and its Applications", Document 90365, Information International Inc., Los Angeles, Calif, January 1972.Google Scholar
- 4.A. K. Griffith, "Handprint Recognition on the GRAFIX I Image Processing System", presented at the 1974 Computer Science Conference, Detroit Michigan, Feb. 4-6, 1974.Google Scholar
- 5.A. K. Griffith, "Preliminary Results of the Handprint Recognition Verifier's Performance on Recantly Acquired Data", Information International Technical Memo 197, November 1973.Google Scholar
- 6.W. S. Rholand, P. J. Traglia, and P. J. Hurley, "The Design of an OCR System for Reading Handwritten Numerals", Proceedings of the Fall Joint Computer Conference, 1968.Google Scholar
- 7.D. L. Casky and C. L. Coates, "Machine Recognition of Handprinted Characters", Technical Report 126, Information System Research Laboratory, Electronics Research Center, The University of Texas, Austin, May 1972.Google Scholar
- 8.J. H. Munson, "Experimants in the Recognition of Hand Printed Text: Part I- Character Recognition", Proceedings of the Fall Joint Computer Conference, 1968.Google Scholar
- 9.S. Katsuragi, H. Genchi, K. Mori, and S. Watanabe, "Recognition of Handwritten Numerals Using Decision Graph ", Proceedings of the First International Joint Conference on Artificial Intelligence, May 1969.Google ScholarDigital Library
- 10.H. Genchi, K-I. Mori, S. Watanabe, and S. Katsuragi, "Recognition of Handwritten Numerical Characters for Automatic Letter Sorting", Proc. IEEE Vol. 56,1968, 1292,1301.Google ScholarCross Ref
- 11.J. T. Tou, and R. C. Gonzalez, "Automatic Recognition of Handwritten Characters via Feature Extraction and Multi-level Decision", The International Journal of Computer and Information Sciences, Vol. 1, No. 1, March 1972, pp. 43-65.Google ScholarCross Ref
- 12.G. T. Toussaint and R. W. Donaldson, "Algorithms for Recognizing Contour-traced Handprinted Characters", IEEE Transactions on Computers (Short Notes), Vol. C-19, pp. 541-546, June 1970.Google Scholar
- 13.W. Teitelman, "Real Time Recognition of Hand-Drawn Characters", AFIPS Proc Fall Joint Computer Conf., 1964, pp. 559-575.Google Scholar
- 14.G. Groner, "Real-time Recognition of Handprinted Text", AFIPS Proc. Fall Joint Computer Conf., 1966, pp. 591-601.Google Scholar
- 15.M. L. Minsky, S. Papert, Perceptrons, MIT Press 1968.Google Scholar
Index Terms
- Handprint recognition on the GRAFIX I:: A commercial application of heuristic programming
Recommendations
A Method of Recognition of Arabic Cursive Handwriting
In spite of the progress of machine recognition techniques of Latin, Kana, and Chinese characters over the two past decades, the machine recognition of Arabic characters has remained almost untouched. In this correspondence, a structural recognition ...
An optical character recognition system for printed Telugu text
Telugu is one of the oldest and popular languages of India, spoken by more than 66 million people, especially in South India. Not much work has been reported on the development of optical character recognition (OCR) systems for Telugu text. Therefore, ...
On-line Hindi handwritten character recognition for mobile devices
ICACCI '12: Proceedings of the International Conference on Advances in Computing, Communications and InformaticsOnline handwriting recognition systems have been developed for various character sets. Despite that, very less attempt has been made to build an online handwriting recognition system for Indian languages. We present an online handwritten isolated ...
Comments