Academic Journals Database
Disseminating quality controlled scientific knowledge

Automatic System for Recognition of Handwritten Character using Multiscale Neural Network

Author(s): Shraddha V. Shelke | D. M. Chandwadkar

Journal: International Journal of Computer Applications
ISSN 0975-8887

Volume: iccia;
Issue: 6;
Date: 2012;
Original page

Keywords: Character recognition | Multiscale | Multilayer perceptron | Decision tree neural network

The constant development of computer tools leads to a requirement of easier interfaces between the man and the computer. Handwritten character recognition may for instance be applied to zip-code recognition, automatic printed form acquisition, or checks reading. The importance of these applications has led to intense research for several years in the field of off-line handwritten character recognition. In this paper character samples with multiple scales i.e. different pixel resolutions are prepared and then neuron is trained in WEKA 3.6 machine learning software for different classifiers. Results observed for different classifiers are compared with each other. If the character images have lower resolution, the training process is much faster. Percentage accuracy increases with increase in resolution of character image.
Save time & money - Smart Internet Solutions      Why do you need a reservation system?