A Neural Approach to Cursive Handwritten Character Recognition Using Features Extracted from Binarization Technique - Complex System Modelling and Control Through Intelligent Soft Computations - page 730

A Neural Approach to Cursive
Handwritten Character Recognition Using
Features Extracted from Binarization
Technique

Amit Choudhary, Savita Ahlawat and Rahul Rishi

Abstract The feature extraction is one of the most crucial steps for an Optical
Character Recognition (OCR) System. The ef

ciency and accuracy of the OCR
System, in recognizing the off-line printed characters, mainly depends on the
selection of feature extraction technique and the classi cation algorithm employed.

This chapter focuses on the recognition of handwritten characters of Roman Script by
using features which are obtained by using binarization technique. The goal of
binarization is to minimize the unwanted information present in the image while
protecting the useful information. Various preprocessing techniques such as thin-
ning, foreground and background noise removal, cropping and size normalization
etc. are also employed to preprocess the character images before their classi cation.

A multi-layered feed forward neural network is proposed for classi cation of

handwritten character images. The difference between the desired and actual output is
calculated for each cycle and the weights are adjusted during error back-propagation.
This process continues till the network converges to the allowable or acceptable error.
This method involves the back propagation-learning rule based on the principle of
gradient descent along the error surface in the negative direction. Very promising
results are achieved when binarization features and the multilayer feed forward
neural network classi

er is used to recognize the off-line cursive handwritten

characters.

Keywords OCR Binarization Feature extraction Character recognition

Back-propagation algorithm Neural network