Error Probability in Decision Functions for Character Recognition

ABSTRACT

Upper bounds for the error probability of a Bayes decision function are derived in terms of the differences among the probability distributions of the features used in character recognition. Applications to feature selection and error reduction are discussed. It is shown that if a sufficient number of well-selected features is used, the error probability can be made arbitrarily small.

REFERENCES

• 1: BERNSTEIN, S. Surextension du theorY.me limite du calcul des probabilits aux sommes de quantits dSpendantes. Math. Ann. 97 (1927), 1-59.
• 2: BLACKWELL, D., AND Gmsmcx, M.A. Theory of Games and Statistical Decisions. Joha Wiley, New York, 1954.
• 3: J. T. Chu, Optimal Decision Functions for Computer Character Recognition, Journal of the ACM (JACM), v.12 n.2, p.213-226, April 1965 [doi>10.1145/321264.321271]
• 4: CRAMAR, H. Mathematical Methods of Statistics. Prkceton U. Press, Princeton, N. J., 1946.
• 5: HOEFFING, W., AND ROBmNS, H. The central limit theorem for dependent random variables. Duke Math. J, 15 (1948), 773-780.
• 6: NILSON, N .J . Learning Machines. McGraw-Hill, New York, 1965o
• 7: NTIONAI., BUREAU OF STADARDS. Tables of Probability Functions. U. S, Government Priiting Office, Washington, D. C., 1950.
• 8: NATIONalS, BUREAU OF STrANDRS Tables of the Binomial Probability Ditribution, U. S, Government Printing OIice Washington D, C. 1950.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.5 PATTERN RECOGNITION
      I.5.2 Design Methodology
          Subjects: Pattern analysis

Additional Classification:
  F. Theory of Computation
  F.4 MATHEMATICAL LOGIC AND FORMAL LANGUAGES
      F.4.3 Formal Languages
          Subjects: Decision problems

General Terms:
Design, Measurement, Performance, Reliability, Theory, Verification