Offline Handwritten Character Recognition Using Improved Back- Propagation Algorithm

Abstract

A neural network is a machine designed to
model the way in which the brain performs a particular
task. Character recognition techniques help in
recognizing the characters written on paper documents
and converting it in digital form. Character recognition
is gaining interest and importance in the modern world
due to its application in various fields. Handwritten
character recognition is a very difficult problem due to
great variation of writing style, different size and shape
of the character. Accuracy and efficiency are the major
parameters in the field of handwritten character
recognition. Neural network is a technique used to
improve the accuracy and efficiency of the handwritten
character recognition system. This paper throws light
on the improved neural network technique to recognize
the offline handwritten characters.