A NEW HYBRID APPROACH IN COMBINING MULTIPLE EXPERTS TO RECOGNIZE HANDWRITTEN NUMERALS

Hand written numeral recognition is an area of pattern recognition tha t has applications in numerous fields including automated postal sorti ng, automatic bank cheque processing, hand written document analysis a nd so on. Recently, the potential advantages of using multiple experts in a unified structure have been demonstrated in addressing the probl em of classification of hand written numerals. The motivation behind t his paper is to implement a new approach to the solution of the proble m of combining the decisions made by multiple experts, by making use o f the restrictive and repetitive nature of the numeral structures and combining the a priori knowledge of the expected numeral classes that are to be processed and recognised with that derived from the training samples. (C) 1997 Elsevier Science B.V.