CLASSIFICATION OF PRINTED TEXT AND HANDWRITTEN CHARACTERS WITH NEURAL NETWORKS

Abstract

Various scanned documents consist of machine printed text as well as handwritten alphabet. The classification of handwritten alphabet and machine printed alphabet in document images is the required process afore character recognition. We can distinguish these two types of alphabet images by their shape structural, statistical and visual difference features. This work proposes the artificial neural network based classification technique for machine printed and handwritten text classification at character level using a set of new features which are combination of statistical, shape structural and visual impression features. The projected technique attained remarkable classification efficiency on two databases; IAM dataset and prepared dataset.