From the above Tab. III, we observe that the recognition
accuracy increases to 92.3 1 % from 88 .46% when we apply
EDM and it further increases to 99.23% when we incorporate
recognition score to the Euclidean distances as a new
approach. Work is going on, we are trying to further improve
the recognition accuracy in terms of data samples and
recognition process time using some other methods and
techniques such as fuzzy logic and hidden Markov models so
as to get the consistency in recognition accuracy. In this paper,
we introduced a new approach which is a combined effect of
the EDM and ANN. We used this new technique only for the
unrecognized characters and get a very good recognition
performance.