EFFECT OF NON-IMAGE FEATURES ON RECOGNITION OF HANDWRITTEN ALPHA-NUMERIC CHARACTERS
Journal Title: INTERNATIONAL JOURNAL OF COMPUTERS & TECHNOLOGY - Year 2014, Vol 13, Issue 11
Abstract
Handwritten character recognition has applications in several industries such as Banking for reading of cheques and Libraries/ National archives for digital searchable storage of historic texts. The main feature typically used for the recognition task is the character image. However, there are other possible features such as the hand (left or right) used by author, number of strokes and other geometric features that can be captured when writing on digital devices. This paper investigates the effect of using some non-image features on the recognition rate of three classifiers: Instance Based Learner (IBk), Support Vector Machines (SVM) and the Multilayer Perceptron (MLP) Neural Network for singly-written alpha-numeric character recognition. Our experiments were conducted using the WEKA machine learning tool on offline and online handwritten acquired locally. A percentage split (66%-34% train-test) evaluation methodology was adopted with the classification accuracy measured. Results indicate that non-image additional features improved the accuracy across the three classifiers for the online and offline character datasets. However, this improvement was not statistically significant. SVM gave the best accuracy for the online dataset while IBk performed better than the other two classifiers for the offline dataset. We intend to investigate the effect of non-image features at other levels of text granularity such as words and sentences
Authors and Affiliations
Ibrahim Adeyanju, Olusayo Fenwa, Elijah Omidiora
Keywords
Related Articles
- EP ID EP650602
- DOI 10.24297/ijct.v13i11.2785
- Views 126
- Downloads 0
Communication Architecture design for an Interoperable Machine-to-Machine System
In recent years, we have witnessed a continuous increase in the number of embedded devices with communication capabilities that are changing the way we live, work and play. Smart grids, remote monitoring and control of...
Parameter Estimation of Reverse Osmosis Process Model for Desalination
The present work pertains to modelling and identification of seawater desalination system using reverse osmosis. Initially the manipulated variable (feed pressure and recycle ratio) and the measured variables (flowrate,...
Development and Simulation of Next Generation SDH Network Management System
In present scenario Network Management System of Next Generation SDH is not performing Offline reporting, offline analysis of alarms, offline performance management and Configurations of network like real time. Any offli...
A Different Learning Way For Pupils With Specific Learning Disabilities
Several factors may contribute to a child's failure to learn, some possible causes of school failure are specific learning disabilities. Dyslexia is one of the most common learning disabilities; dyslexia is to fail to le...
Retrieving information chunks from a repository of documents SIT Collected from heterogeneous sources
XML documents are generated from heterogeneous resources. They may share the same data but in different Schema, which make it difficult to retrieve information from them. In this paper we propose a new technique that fir...