Title :
A high precision printed character recognition method for Tamil script
Author :
Sundar, K. Ajay ; John, Michael
Author_Institution :
Dept. of Electron. Eng., Anna Univ., Chennai, India
Abstract :
In this paper, we describe an efficient printed Tamil character recognition method developed for an omni font case using HOG (Histogram of Oriented Gradients) features. A Back propagated Neural Networks classifier is used at the original classification stage, which is followed by a secondary FLDA (Fischer Linear Discriminant Analysis) classifier to overcome the misclassifications by the BPN network. An algorithmic fusion approach is used to improve the accuracy of the primary classifier. A comparison of the performance of the proposed classification technique with different features is also provided. There is no benchmark database to conduct studies on the printed Tamil character recognition. So, a database of 3670 samples of varying sizes with 35 font types has been created for our research.
Keywords :
backpropagation; feature extraction; image classification; natural languages; neural nets; optical character recognition; BPN network; HOG features; Tamil script; algorithmic fusion approach; backpropagated neural network classifier; benchmark database; high precision printed Tamil character recognition method; histogram of oriented gradient features; secondary FLDA classifier; secondary Fischer linear discriminant analysis classifier; Accuracy; Character recognition; Conferences; Feature extraction; Histograms; Neural networks; Optical character recognition software; FDA; Histogram of Oriented Gradients (HOG); Tamil character recognition; backpropagated neural networks; offline character recognition;
Conference_Titel :
Computational Intelligence and Computing Research (ICCIC), 2013 IEEE International Conference on
Conference_Location :
Enathi
Print_ISBN :
978-1-4799-1594-1
DOI :
10.1109/ICCIC.2013.6724285
